{"id":"https://openalex.org/W7161273521","doi":"https://doi.org/10.48550/arxiv.2605.14635","title":"MultiEmo-Bench: Multi-label Visual Emotion Analysis for Multi-modal Large Language Models","display_name":"MultiEmo-Bench: Multi-label Visual Emotion Analysis for Multi-modal Large Language Models","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161273521","doi":"https://doi.org/10.48550/arxiv.2605.14635"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.14635","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.14635","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101534861","display_name":"Tianwei Chen","orcid":"https://orcid.org/0000-0002-2544-7744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Tianwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136254575","display_name":"Takuya Furusawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Furusawa, Takuya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109032670","display_name":"Yuki Hirakawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hirakawa, Yuki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136247433","display_name":"Ryotaro Shimizu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shimizu, Ryotaro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136247339","display_name":"Mo Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Mo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136253551","display_name":"Takashi Wada","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wada, Takashi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.746399998664856,"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"}},"topics":[{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.746399998664856,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.08630000054836273,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.053700000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8337000012397766},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.47530001401901245},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.4514999985694885},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4318999946117401},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.42800000309944153},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.3928000032901764}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8337000012397766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766700029373169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5924000144004822},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46700000762939453},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4296000003814697},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.14635","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.14635","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,83],"paper":[1],"introduces":[2],"a":[3,68,89,100,129,168,176],"multi-label":[4,131],"visual":[5,135,264],"emotion":[6,71,136,217,220,265],"analysis":[7,137],"benchmark":[8,116,132,196],"dataset":[9,133,173,182],"for":[10,72,117,134,238,259],"comprehensively":[11],"evaluating":[12,118],"the":[13,23,38,43,55,109,162,226,248,260],"ability":[14],"of":[15,40,111,178,263],"multimodal":[16],"large":[17],"language":[18],"models":[19,120],"(MLLMs)":[20],"to":[21,150],"predict":[22],"emotions":[24,95,153],"evoked":[25,80],"by":[26,229],"images.":[27],"Recent":[28],"user":[29],"studies":[30],"report":[31],"an":[32,114,157],"unintuitive":[33],"finding:":[34],"humans":[35],"may":[36,107],"prefer":[37],"predictions":[39],"MLLMs":[41,139,231],"over":[42],"labels":[44],"in":[45,60],"existing":[46,61],"datasets.":[47],"We":[48,141,210],"argue":[49],"that":[50,235,247],"this":[51,125,195],"phenomenon":[52],"stems":[53],"from":[54,156],"suboptimal":[56],"annotation":[57],"scheme":[58],"used":[59],"datasets,":[62],"where":[63],"each":[64,73],"annotator":[65],"is":[66,79,85],"shown":[67],"single":[69,90],"candidate":[70],"image":[74,91,146],"and":[75,147,171,208,219],"judges":[76],"whether":[77],"it":[78],"or":[81],"not.":[82],"approach":[84],"clearly":[86],"limited":[87],"because":[88],"can":[92],"evoke":[93],"multiple":[94],"with":[96,175,186,244],"varying":[97],"intensities.":[98],"As":[99],"result,":[101],"evaluations":[102],"based":[103],"on":[104,194,214],"these":[105],"datasets":[106],"underestimate":[108],"capabilities":[110],"MLLMs,":[112],"yet":[113],"appropriate":[115],"such":[119],"remains":[121],"lacking.":[122],"To":[123],"address":[124],"issue,":[126],"we":[127,160,198],"introduce":[128],"new":[130],"toward":[138],"evaluation.":[140],"hire":[142],"$20$":[143],"annotators":[144],"per":[145],"ask":[148],"them":[149],"select":[151],"all":[152,165],"they":[154],"feel":[155],"image.":[158],"Then,":[159],"aggregate":[161],"votes":[163,189],"across":[164,190],"annotators,":[166],"providing":[167],"more":[169],"reliable":[170],"representative":[172],"labeled":[174],"distribution":[177,221],"emotions.":[179,192],"The":[180],"resulting":[181],"contains":[183],"$10,344$":[184],"images":[185],"$236,998$":[187],"valid":[188],"eight":[191],"Based":[193],"dataset,":[197],"evaluate":[199],"several":[200],"recent":[201,230],"models,":[202],"including":[203],"Qwen3-VL,":[204],"OpenAI's":[205],"GPT,":[206],"Gemini,":[207],"Claude.":[209],"assess":[211],"model":[212],"performance":[213],"both":[215],"dominant":[216],"prediction":[218],"prediction.":[222],"Our":[223],"results":[224],"demonstrate":[225],"progress":[227],"achieved":[228],"while":[232],"also":[233],"indicating":[234,256],"substantial":[236],"room":[237],"improvement":[239],"remains.":[240],"Furthermore,":[241],"our":[242],"experiments":[243],"LLM-as-a-judge":[245],"show":[246],"method":[249],"does":[250],"not":[251],"consistently":[252],"improve":[253],"MLLMs'":[254],"performance,":[255],"its":[257],"limitations":[258],"subjective":[261],"task":[262],"analysis.":[266]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-16T00:00:00"}