{"id":"https://openalex.org/W7138416851","doi":"https://doi.org/10.1609/aaai.v40i10.37726","title":"Regression over Classification: Assessing Image Aesthetics via Multimodal Large Language Models","display_name":"Regression over Classification: Assessing Image Aesthetics via Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138416851","doi":"https://doi.org/10.1609/aaai.v40i10.37726"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i10.37726","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37726","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37726/41688","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://ojs.aaai.org/index.php/AAAI/article/download/37726/41688","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129725973","display_name":"Xingyuan Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyuan Ma","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129690777","display_name":"Shuai He","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai He","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082092902","display_name":"Anlong Ming","orcid":"https://orcid.org/0000-0003-2952-7757"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anlong Ming","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068051339","display_name":"Haobin Zhong","orcid":"https://orcid.org/0000-0001-7514-3709"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobin Zhong","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121004282","display_name":"Huadong Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huadong Ma","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"7827","last_page":"7835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.6984999775886536,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.6984999775886536,"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":0.0908999964594841,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0494999997317791,"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/security-token","display_name":"Security token","score":0.49549999833106995},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4480000138282776},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.44029998779296875},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4300999939441681},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.39320001006126404},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.36970001459121704},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3677000105381012},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.3643999993801117},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.34470000863075256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6970000267028809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5407000184059143},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4562999904155731},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3504999876022339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3465999960899353},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3343000113964081},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C78780964","wikidata":"https://www.wikidata.org/wiki/Q7233193","display_name":"Position paper","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C2993924013","wikidata":"https://www.wikidata.org/wiki/Q6486792","display_name":"Receptive language","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i10.37726","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37726","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37726/41688","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/37726","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37726","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.v40i10.37726","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37726","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37726/41688","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":[{"score":0.7944764494895935,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138416851.pdf","grobid_xml":"https://content.openalex.org/works/W7138416851.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"Aesthetics":[1],"Assessment":[2],"(IAA)":[3],"evaluates":[4],"visual":[5],"quality":[6],"through":[7],"user-centered":[8],"perceptual":[9],"analysis":[10],"and":[11,51,135,160],"can":[12],"guide":[13],"various":[14],"applications.":[15],"Recent":[16],"advances":[17],"in":[18,27,37,124,162],"Multimodal":[19],"Large":[20],"Language":[21],"Models":[22],"(MLLMs)":[23],"have":[24],"sparked":[25],"interest":[26],"adapting":[28],"them":[29],"for":[30,133],"IAA.":[31],"However,":[32],"two":[33,91],"critical":[34],"limitations":[35],"persist":[36],"applying":[38],"MLLMs":[39],"to":[40,47,49,102,121,138,145],"IAA:":[41],"1)":[42],"the":[43,53,66,98,116,119,140,143,163],"tokenization":[44],"strategy":[45],"leads":[46],"insensitivity":[48],"scores,":[50],"2)":[52,126],"classification-based":[54],"decoding":[55],"mechanisms":[56],"introduce":[57],"score":[58,122,136,146],"quantization":[59],"errors.":[60],"Current":[61],"MLLM-based":[62],"IAA":[63,194],"methods":[64],"treat":[65],"task":[67],"as":[68,106],"coarse":[69],"rating":[70],"classification":[71],"followed":[72],"by":[73],"probability-to-score":[74],"mapping,":[75],"which":[76],"loses":[77],"fine-grained":[78],"information.":[79],"To":[80],"address":[81],"these":[82,113],"challenges,":[83],"we":[84],"propose":[85],"ROC4MLLM,":[86],"offering":[87],"complementary":[88],"solutions":[89],"from":[90,97,150],"perspectives:1)":[92],"Representation:":[93],"We":[94,128],"separate":[95],"scores":[96,105,149,159],"word":[99],"token":[100,111],"space":[101],"avoid":[103],"tokenizing":[104],"text.":[107,125],"An":[108],"independent":[109],"position":[110],"bridges":[112],"spaces,":[114],"improving":[115],"sensitivity":[117,141],"of":[118,142],"model":[120,144],"positions":[123],"Computation:":[127],"apply":[129],"distinct":[130],"loss":[131,164],"functions":[132],"text":[134,151,161],"predictions":[137],"enhance":[139],"gradients.":[147],"Decoupling":[148],"ensures":[152,186],"effective":[153],"supervision":[154],"while":[155],"preventing":[156],"interference":[157],"between":[158],"computation.":[165],"Extensive":[166],"experiments":[167],"across":[168],"five":[169],"datasets":[170],"demonstrate":[171],"that":[172],"ROC4MLLM":[173],"achieves":[174],"state-of-the-art":[175],"performance":[176],"without":[177],"requiring":[178],"additional":[179],"training":[180],"data.":[181],"Additionally,":[182],"its":[183],"plug-and-play":[184],"design":[185],"seamless":[187],"integration":[188],"with":[189],"existing":[190],"MLLMs,":[191],"boosting":[192],"their":[193],"performance.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}