{"id":"https://openalex.org/W4390962869","doi":"https://doi.org/10.48550/arxiv.2401.08276","title":"AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception","display_name":"AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception","publication_year":2024,"publication_date":"2024-01-16","ids":{"openalex":"https://openalex.org/W4390962869","doi":"https://doi.org/10.48550/arxiv.2401.08276"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2401.08276","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.08276","pdf_url":"https://arxiv.org/pdf/2401.08276","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.08276","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016576297","display_name":"Yipo Huang","orcid":"https://orcid.org/0000-0003-0908-2180","observed_orcids":["https://orcid.org/0000-0003-0908-2180"]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Yipo","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuan, Quan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan, Quan","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044278717","display_name":"Xiangfei Sheng","orcid":"https://orcid.org/0009-0004-8468-1970","observed_orcids":["https://orcid.org/0009-0004-8468-1970"]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng, Xiangfei","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102605944","display_name":"Zhichao Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Zhichao","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014879869","display_name":"Haoning Wu","orcid":"https://orcid.org/0000-0001-8642-8101","observed_orcids":["https://orcid.org/0000-0001-8642-8101"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wu, Haoning","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Pengfei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Pengfei","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027089869","display_name":"Yuzhe Yang","orcid":"https://orcid.org/0000-0001-9098-2105","observed_orcids":["https://orcid.org/0000-0001-9098-2105"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yuzhe","raw_affiliation_strings":["OPPO Research Institute {huangyipo ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO Research Institute {huangyipo ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033615240","display_name":"Leida Li","orcid":"https://orcid.org/0000-0001-9069-8796","observed_orcids":["https://orcid.org/0000-0001-9069-8796"]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Leida","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403129","display_name":"Weisi Lin","orcid":"https://orcid.org/0000-0001-9866-1947","observed_orcids":["https://orcid.org/0000-0001-9866-1947"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lin, Weisi","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":90,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9785000085830688,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9785000085830688,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.006500000134110451,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.004000000189989805,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9100000262260437},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.6019999980926514},{"id":"https://openalex.org/keywords/aesthetic-empathy","display_name":"aesthetic empathy","score":0.47600001096725464},{"id":"https://openalex.org/keywords/aesthetic-interpretation","display_name":"aesthetic interpretation","score":0.734000027179718}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7550747990608215},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5495948195457458},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5399965643882751},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46793457865715027},{"id":"https://openalex.org/C2781017355","wikidata":"https://www.wikidata.org/wiki/Q5462027","display_name":"Flourishing","level":2,"score":0.46353578567504883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46318885684013367},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.39987024664878845},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.37611255049705505},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.16467618942260742},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.16350844502449036},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2401.08276","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.08276","pdf_url":"https://arxiv.org/pdf/2401.08276","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2401.08276","doi":"https://doi.org/10.48550/arxiv.2401.08276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.08276","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.08276","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.08276","pdf_url":"https://arxiv.org/pdf/2401.08276","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390962869.pdf","grobid_xml":"https://content.openalex.org/works/W4390962869.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2964137521","https://openalex.org/W3135367836","https://openalex.org/W4287265459","https://openalex.org/W4322718191","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4376312115","https://openalex.org/W4385570204","https://openalex.org/W4386185600","https://openalex.org/W4386211581","https://openalex.org/W4387010079","https://openalex.org/W4387076386","https://openalex.org/W4387294588","https://openalex.org/W4387723654","https://openalex.org/W4389519489","https://openalex.org/W4390437716","https://openalex.org/W4390438010","https://openalex.org/W4401990587","https://openalex.org/W4402704606","https://openalex.org/W4402727669","https://openalex.org/W4402727764","https://openalex.org/W4402754134","https://openalex.org/W4403943260","https://openalex.org/W4404575065","https://openalex.org/W4410536678","https://openalex.org/W7128730772","https://openalex.org/W7133239970"],"related_works":["https://openalex.org/W4403792379","https://openalex.org/W4416157480","https://openalex.org/W7161166458","https://openalex.org/W4408345879","https://openalex.org/W4415251340","https://openalex.org/W4416036908","https://openalex.org/W7083694777","https://openalex.org/W4417429024","https://openalex.org/W7204524908","https://openalex.org/W4413157130"],"abstract_inverted_index":{"With":[0],"collective":[1],"endeavors,":[2],"multimodal":[3],"large":[4],"language":[5],"models":[6],"(MLLMs)":[7],"are":[8],"undergoing":[9],"a":[10,37,116,160],"flourishing":[11],"development.":[12],"However,":[13],"their":[14],"performances":[15],"on":[16,46,180],"image":[17,103],"aesthetics":[18],"perception":[19,63,81,125,154],"remain":[20],"indeterminate,":[21],"which":[22,100],"is":[23,158],"highly":[24],"desired":[25],"in":[26,33,177],"real-world":[27],"applications.":[28],"An":[29],"obvious":[30],"obstacle":[31],"lies":[32],"the":[34,42,54,79,123,147,173,181],"absence":[35],"of":[36,44,57,83,118,127,184],"specific":[38],"benchmark":[39,74],"to":[40,76,121,175],"evaluate":[41,78],"effectiveness":[43],"MLLMs":[45,60,84,128,149,164],"aesthetic":[47,62,80,111,124,153,182],"perception.":[48],"This":[49],"blind":[50],"groping":[51],"may":[52],"impede":[53],"further":[55],"development":[56],"more":[58],"advanced":[59],"with":[61],"capacity.":[64],"To":[65],"address":[66],"this":[67,169],"dilemma,":[68],"we":[69],"propose":[70,115],"AesBench,":[71],"an":[72,94],"expert":[73],"aiming":[75],"comprehensively":[77],"capacities":[82],"through":[85],"elaborate":[86],"design":[87],"across":[88],"dual":[89],"facets.":[90],"(1)":[91],"We":[92,114,167],"construct":[93],"Expert-labeled":[95],"Aesthetics":[96],"Perception":[97,133],"Database":[98],"(EAPD),":[99],"features":[101],"diversified":[102],"contents":[104],"and":[105,139,156,165],"high-quality":[106],"annotations":[107],"provided":[108],"by":[109],"professional":[110],"experts.":[112],"(2)":[113],"set":[117],"integrative":[119],"criteria":[120],"measure":[122],"abilities":[126],"from":[129],"four":[130],"perspectives,":[131],"including":[132],"(AesP),":[134],"Empathy":[135],"(AesE),":[136],"Assessment":[137],"(AesA)":[138],"Interpretation":[140],"(AesI).":[141],"Extensive":[142],"experimental":[143],"results":[144],"underscore":[145],"that":[146],"current":[148],"only":[150],"possess":[151],"rudimentary":[152],"ability,":[155],"there":[157],"still":[159],"significant":[161],"gap":[162],"between":[163],"humans.":[166],"hope":[168],"work":[170],"can":[171],"inspire":[172],"community":[174],"engage":[176],"deeper":[178],"explorations":[179],"potentials":[183],"MLLMs.":[185],"Source":[186],"data":[187],"will":[188],"be":[189],"available":[190],"at":[191],"https://github.com/yipoh/AesBench.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":41},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":21}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-01-18T00:00:00"}