{"id":"https://openalex.org/W4415707989","doi":"https://doi.org/10.1109/icme59968.2025.11209018","title":"Fine-tuned Multimodal Large Language Models are Zero-shot Learners in Image Quality Assessment","display_name":"Fine-tuned Multimodal Large Language Models are Zero-shot Learners in Image Quality Assessment","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707989","doi":"https://doi.org/10.1109/icme59968.2025.11209018"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5106405406","display_name":"Rui Xiong","orcid":"https://orcid.org/0009-0006-2212-1446"},"institutions":[{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xiong","raw_affiliation_strings":["Wuhan University of Science and Technology,School of Computer Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Science and Technology,School of Computer Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I43922553"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379203","display_name":"Li Chen","orcid":"https://orcid.org/0000-0001-9899-2535"},"institutions":[{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Chen","raw_affiliation_strings":["Wuhan University of Science and Technology,School of Computer Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Science and Technology,School of Computer Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I43922553"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112395293","display_name":"Zhida Feng","orcid":"https://orcid.org/0009-0004-6348-9621"},"institutions":[{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhida Feng","raw_affiliation_strings":["Wuhan University of Science and Technology,School of Computer Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Science and Technology,School of Computer Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I43922553"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100721391","display_name":"Jiaxiang Liu","orcid":"https://orcid.org/0000-0002-8851-3155"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxiang Liu","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005049423","display_name":"Shikun Feng","orcid":"https://orcid.org/0000-0002-0191-4854"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikun Feng","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.8230999708175659,"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":0.8230999708175659,"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":0.05339999869465828,"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/T11019","display_name":"Image Enhancement Techniques","score":0.02710000053048134,"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/semantics","display_name":"Semantics (computer science)","score":0.5863000154495239},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5052000284194946},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.476500004529953},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4643999934196472},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4512999951839447},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4499000012874603},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4375},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.42669999599456787},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41519999504089355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6326000094413757},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46549999713897705},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4643999934196472},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4375},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41519999504089355},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3474000096321106},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.31369999051094055},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1979451680","https://openalex.org/W2148848374","https://openalex.org/W2161907179","https://openalex.org/W2171349048","https://openalex.org/W2905544033","https://openalex.org/W2953590133","https://openalex.org/W3002992380","https://openalex.org/W3030380536","https://openalex.org/W3035719652","https://openalex.org/W3185577028","https://openalex.org/W3194280054","https://openalex.org/W4214745154","https://openalex.org/W4221144351","https://openalex.org/W4229077902","https://openalex.org/W4312966191","https://openalex.org/W4382462760","https://openalex.org/W4386076169","https://openalex.org/W4386211581","https://openalex.org/W4387010079","https://openalex.org/W4391490252","https://openalex.org/W4402713111","https://openalex.org/W4410706693"],"related_works":[],"abstract_inverted_index":{"Image":[0],"quality":[1,62,129],"assessment":[2],"(IQA)":[3],"has":[4],"traditionally":[5],"relied":[6],"on":[7],"task-specific":[8],"models,":[9],"often":[10],"limiting":[11],"their":[12,91,100],"adaptability":[13],"and":[14,61,80,90,99,118,123],"generalization":[15],"to":[16,83,108,126],"diverse":[17],"image":[18],"content.":[19],"To":[20,65],"this":[21,23,46],"end,":[22],"paper":[24,47,70],"introduces":[25],"LV-IQA,":[26],"a":[27,52,72,110],"fine-tuned":[28],"Multimodal":[29],"Large":[30],"Language":[31],"Model":[32],"(MLLM)":[33],"via":[34],"Visual":[35],"Grounding,":[36],"demonstrating":[37],"zero-shot":[38,138],"learning":[39],"in":[40,58,140],"IQA.":[41,141],"The":[42],"key":[43],"contributions":[44],"of":[45,51,55,113,120,130],"involve":[48],"the":[49,69,85,96,116,128,131],"proposal":[50],"cross-modal":[53],"chain":[54,112],"thought":[56],"rooted":[57],"hierarchical":[59,92],"semantics":[60],"levels.":[63],"Additionally,":[64],"enhance":[66],"its":[67],"adaptability,":[68],"incorporates":[71],"visual":[73,102],"grounding":[74,103],"prompt":[75],"generated":[76],"through":[77],"segmentation":[78],"masks":[79],"bounding":[81],"boxes":[82],"learn":[84],"correspondence":[86],"between":[87],"original":[88,97],"images":[89,98],"semantics.":[93],"By":[94],"observing":[95],"corresponding":[101],"information,":[104],"LV-IQA":[105,135],"is":[106],"empowered":[107],"employ":[109],"sophisticated":[111],"thought,":[114],"involving":[115],"perception":[117],"comprehension":[119],"local":[121],"details":[122],"area":[124],"structures,":[125],"infer":[127],"images.":[132],"Through":[133],"experiments,":[134],"demonstrates":[136],"reliable":[137],"capabilities":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}