{"id":"https://openalex.org/W7225319665","doi":"https://doi.org/10.1145/3767308.3836240","title":"Generalizable Blind Image Quality Assessment with Retrieval Augmentation and Contrastive Vision-Text Local Meta-Training","display_name":"Generalizable Blind Image Quality Assessment with Retrieval Augmentation and Contrastive Vision-Text Local Meta-Training","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225319665","doi":"https://doi.org/10.1145/3767308.3836240"},"language":"en","primary_location":{"id":"doi:10.1145/3767308.3836240","doi":"https://doi.org/10.1145/3767308.3836240","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767308.3836240","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"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 34th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3767308.3836240","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101454332","display_name":"Yan Zhong","orcid":"https://orcid.org/0000-0003-0005-2620","observed_orcids":["https://orcid.org/0000-0003-0005-2620"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhong","raw_affiliation_strings":["School of Mathematical Sciences, State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0005-2620","affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113315332","display_name":"Zhiyuan You","orcid":"https://orcid.org/0009-0006-8546-3478","observed_orcids":["https://orcid.org/0009-0006-8546-3478"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiyuan You","raw_affiliation_strings":["MMLab, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0006-8546-3478","affiliations":[{"raw_affiliation_string":"MMLab, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082323642","display_name":"Xinping Zhao","orcid":"https://orcid.org/0000-0001-6387-1442","observed_orcids":["https://orcid.org/0000-0001-6387-1442"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinping Zhao","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6387-1442","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425448","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-7914-0679","observed_orcids":["https://orcid.org/0000-0001-7914-0679","https://orcid.org/0000-0003-1610-6056"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Hefei Institute of Physical Science, Chinese Academy of Sciences, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1610-6056","affiliations":[{"raw_affiliation_string":"Hefei Institute of Physical Science, Chinese Academy of Sciences, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I2802624667"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100565377","display_name":"Song Xin-yuan","orcid":"https://orcid.org/0009-0005-4209-5671","observed_orcids":["https://orcid.org/0009-0005-4209-5671","https://orcid.org/0000-0002-7760-6399","https://orcid.org/0000-0003-3414-3117"]},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyuan Song","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas at Arlington, Arlington, Texas, USA"],"raw_orcid":"https://orcid.org/0009-0005-4209-5671","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas at Arlington, Arlington, Texas, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095333375","display_name":"Ruoyu Zhao","orcid":"https://orcid.org/0009-0008-8170-4208","observed_orcids":["https://orcid.org/0009-0008-8170-4208"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ruoyu Zhao","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0008-8170-4208","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052255801","display_name":"Lei Shi","orcid":"https://orcid.org/0000-0002-5570-7818","observed_orcids":["https://orcid.org/0000-0002-5570-7818"]},"institutions":[{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Shi","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5570-7818","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101606698","display_name":"Tingting Jiang","orcid":"https://orcid.org/0000-0002-5372-0656","observed_orcids":["https://orcid.org/0000-0002-5372-0656"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Jiang","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, State Key Laboratory for Multimedia Information Processing, School of Computer Science, National Biomedical Imaging Center, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5372-0656","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, State Key Laboratory for Multimedia Information Processing, School of Computer Science, National Biomedical Imaging Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84467592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15812","last_page":"15821"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.989300012588501,"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":0.989300012588501,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.005499999970197678,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.0013000000035390258,"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/no-reference-image-quality-assessment","display_name":"no-reference image quality assessment","score":0.996999979019165},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.7419999837875366},{"id":"https://openalex.org/keywords/retrieval-augmentation","display_name":"retrieval augmentation","score":0.7829999923706055},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.8939999938011169},{"id":"https://openalex.org/keywords/zero-shot-prediction","display_name":"zero-shot prediction","score":0.5490000247955322},{"id":"https://openalex.org/keywords/image-distortion","display_name":"image distortion","score":0.4620000123977661}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5954999923706055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5781000256538391},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4993000030517578},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.43230000138282776},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.3296999931335449},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767308.3836240","doi":"https://doi.org/10.1145/3767308.3836240","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767308.3836240","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"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 34th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3767308.3836240","doi":"https://doi.org/10.1145/3767308.3836240","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767308.3836240","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"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 34th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1816313093","https://openalex.org/W1977725648","https://openalex.org/W2138790992","https://openalex.org/W2161907179","https://openalex.org/W2518108298","https://openalex.org/W2593864460","https://openalex.org/W2597655663","https://openalex.org/W2610808748","https://openalex.org/W2908510526","https://openalex.org/W2953590133","https://openalex.org/W3002992380","https://openalex.org/W3035712445","https://openalex.org/W3090767700","https://openalex.org/W3094502228","https://openalex.org/W3109016160","https://openalex.org/W3111425437","https://openalex.org/W3130885914","https://openalex.org/W3194280054","https://openalex.org/W4213277345","https://openalex.org/W4252841025","https://openalex.org/W4293518729","https://openalex.org/W4297808394","https://openalex.org/W4319336354","https://openalex.org/W4367146870","https://openalex.org/W4382462760","https://openalex.org/W4386071514","https://openalex.org/W4386071753","https://openalex.org/W4386076169","https://openalex.org/W4386211581","https://openalex.org/W4389984066","https://openalex.org/W4392543651","https://openalex.org/W4394593145","https://openalex.org/W4401109572","https://openalex.org/W4403511232","https://openalex.org/W4409367947","https://openalex.org/W4411996630","https://openalex.org/W4413146182","https://openalex.org/W4415150909","https://openalex.org/W4415538203","https://openalex.org/W4415538374","https://openalex.org/W4415709314","https://openalex.org/W7117117861","https://openalex.org/W7127340636","https://openalex.org/W7138073530","https://openalex.org/W7166089320","https://openalex.org/W7166142209","https://openalex.org/W7166528749","https://openalex.org/W7166815598","https://openalex.org/W7166894752"],"related_works":["https://openalex.org/W7159961840","https://openalex.org/W7215092471","https://openalex.org/W4409968662","https://openalex.org/W7224367941","https://openalex.org/W4235942131","https://openalex.org/W2894368463","https://openalex.org/W4410801027","https://openalex.org/W2748795498","https://openalex.org/W7222268758","https://openalex.org/W7145735881"],"abstract_inverted_index":{"While":[0],"existing":[1],"CLIP-based":[2,77],"Image":[3],"Quality":[4],"Assessment":[5],"(IQA)":[6],"models":[7,49],"have":[8,43],"demonstrated":[9],"enhanced":[10],"capabilities":[11],"in":[12],"perceiving":[13],"visual":[14],"quality,":[15],"due":[16],"to":[17,27,46,50,94,117,141,171],"the":[18,35,57,98,121,132,139,143,149,157,179,182,200],"small":[19],"scale":[20,59],"of":[21,60,97,151,181,204],"IQA":[22,48,61,79],"datasets,":[23,56],"they":[24],"still":[25,63],"struggle":[26],"evaluate":[28],"out-of-distribution":[29],"distorted":[30],"images,":[31],"which":[32,92,153],"deviate":[33],"from":[34,138,193],"pre-training":[36,115],"datasets.":[37],"Although":[38],"some":[39],"mixed-dataset":[40],"training":[41,150],"methods":[42],"been":[44],"proposed":[45],"enable":[47],"be":[51,212],"trained":[52],"on":[53],"more":[54],"diverse":[55],"limited":[58],"data":[62],"restricts":[64],"these":[65,71],"methods'":[66],"generalization":[67,186,203],"ability.":[68],"To":[69],"address":[70],"issues,":[72],"we":[73,110,165,177],"propose":[74,112,166],"a":[75,167,194],"novel":[76],"blind":[78],"method":[80],"named":[81],"R":[82],"etrieval-":[83],"e":[84],"nhanced":[85],"loca":[86],"l":[87],"meta":[88],"t":[89],"raining":[90],"(Relocat)-IQA,":[91],"aims":[93],"augment":[95],"both":[96],"image":[99,144],"and":[100,119,145,202,209],"text":[101,146],"embeddings":[102,147],"by":[103],"online":[104],"retrieval":[105],"for":[106,185],"better":[107],"generalization.":[108],"Specifically,":[109],"first":[111],"an":[113,127],"effective":[114],"framework":[116],"align":[118],"encode":[120],"fine-grained":[122],"multi-modal":[123],"quality":[124,134],"knowledge":[125,135],"as":[126],"external":[128],"embedding":[129],"memory.":[130],"Then":[131],"sample-specific":[133],"is":[136],"retrieved":[137],"memory":[140],"enhance":[142],"during":[148],"\\method,":[152],"can":[154,211],"greatly":[155],"improve":[156],"zero-shot":[158],"predictions":[159],"at":[160,214],"inference":[161],"time.":[162],"In":[163],"addition,":[164],"local":[168],"meta-training":[169],"strategy":[170],"utilize":[172],"mixed":[173],"datasets":[174],"efficiently.":[175],"Remarkably,":[176],"demonstrate":[178],"benefits":[180],"retrieval-enhanced":[183],"module":[184],"not":[187],"only":[188],"through":[189],"experiments":[190,198],"but":[191],"also":[192],"theoretical":[195],"perspective.":[196],"Extensive":[197],"validate":[199],"effectiveness":[201],"our":[205],"method.":[206],"Supp.":[207],"Mat.":[208],"details":[210],"found":[213],"https://github.com/zhyan567/Relocat-IQA.":[215]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-06T00:00:00"}