{"id":"https://openalex.org/W7138008195","doi":"https://doi.org/10.1609/aaai.v40i11.37908","title":"Revisiting MLLM Based Image Quality Assessment: Errors and Remedy","display_name":"Revisiting MLLM Based Image Quality Assessment: Errors and Remedy","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138008195","doi":"https://doi.org/10.1609/aaai.v40i11.37908"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i11.37908","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37908","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37908/41870","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/37908/41870","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121916011","display_name":"Zhenchen Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenchen Tang","raw_affiliation_strings":["New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129665161","display_name":"Songlin Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Songlin Yang","raw_affiliation_strings":["MMLab@HKUST, The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MMLab@HKUST, The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129689800","display_name":"Bo Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Peng","raw_affiliation_strings":["New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129657395","display_name":"Zichuan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zichuan Wang","raw_affiliation_strings":["New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129658825","display_name":"Jing Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Dong","raw_affiliation_strings":["New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"11","first_page":"9475","last_page":"9483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.8816999793052673,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.8816999793052673,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.020800000056624413,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.011300000362098217,"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":0.6784999966621399},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5927000045776367},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.5681999921798706},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5454999804496765},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46160000562667847},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4447999894618988},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.427700012922287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738000154495239},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6784999966621399},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5927000045776367},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.5681999921798706},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5404000282287598},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37209999561309814},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3617999851703644},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.3262999951839447},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2596000134944916}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i11.37908","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37908","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37908/41870","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i11.37908","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37908","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37908/41870","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138008195.pdf","grobid_xml":"https://content.openalex.org/works/W7138008195.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"progress":[2],"of":[3,13,32,38,51,84,106],"multi-modal":[4],"large":[5],"language":[6],"models":[7],"(MLLMs)":[8],"has":[9],"boosted":[10],"the":[11,24,28,35,49,71,82,107,137],"task":[12],"image":[14],"quality":[15,39],"assessment":[16],"(IQA).":[17],"However,":[18],"a":[19,103,119,128],"key":[20],"challenge":[21],"arises":[22],"from":[23,67],"inherent":[25,109],"mismatch":[26],"between":[27],"discrete":[29,59],"token":[30,60],"outputs":[31],"MLLMs":[33,85],"and":[34,89,132,157],"continuous":[36,63],"nature":[37],"scores":[40,64],"required":[41],"by":[42,75,115],"IQA":[43,53,87,150],"tasks.":[44,96],"This":[45,125],"discrepancy":[46],"significantly":[47],"hinders":[48],"performance":[50,83,147],"MLLM-based":[52],"methods.":[54,163],"Previous":[55],"approaches":[56,112],"that":[57,143],"convert":[58],"predictions":[61],"into":[62,136],"often":[65],"suffer":[66],"conversion":[68],"errors.":[69],"Moreover,":[70],"semantic":[72],"confusion":[73],"introduced":[74],"level":[76],"tokens":[77,135],"(e.g.,":[78],"\u201cgood\u201d)":[79],"further":[80,158],"constrains":[81],"on":[86],"tasks":[88],"degrades":[90],"their":[91],"original":[92],"capabilities":[93],"to":[94,154],"related":[95],"To":[97],"tackle":[98],"these":[99],"problems,":[100],"we":[101],"provide":[102],"theoretical":[104],"analysis":[105],"errors":[108],"in":[110],"previous":[111],"and,":[113],"motivated":[114],"this":[116],"analysis,":[117],"propose":[118],"simple":[120],"yet":[121],"effective":[122],"framework,":[123],"Q-Scorer.":[124],"framework":[126],"incorporates":[127],"lightweight":[129],"regression":[130],"module":[131],"IQA-specific":[133],"score":[134],"MLLM":[138],"pipeline.":[139],"Extensive":[140],"experiments":[141],"demonstrate":[142],"Q-Scorer":[144],"achieves":[145],"state-of-the-art":[146],"across":[148],"multiple":[149],"benchmarks,":[151],"generalizes":[152],"well":[153],"mixed":[155],"datasets,":[156],"improves":[159],"combined":[160],"with":[161],"other":[162]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}