{"id":"https://openalex.org/W4415254229","doi":"https://doi.org/10.1109/wacv61042.2026.00525","title":"Revisiting Vision\u2013Language Foundations for No-Reference Image Quality Assessment","display_name":"Revisiting Vision\u2013Language Foundations for No-Reference Image Quality Assessment","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4415254229","doi":"https://doi.org/10.1109/wacv61042.2026.00525"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.17374","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100726938","display_name":"Ankit Yadav","orcid":"https://orcid.org/0009-0003-9137-7670"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ankit Yadav","raw_affiliation_strings":["The University of Adelaide,Adelaide,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide,Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064518233","display_name":"Ta Duc Huy","orcid":"https://orcid.org/0000-0001-6181-0478"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ta Duc Huy","raw_affiliation_strings":["The University of Adelaide,Adelaide,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide,Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070976480","display_name":"Lingqiao Liu","orcid":"https://orcid.org/0000-0003-3584-795X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lingqiao Liu","raw_affiliation_strings":["The University of Adelaide,Adelaide,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide,Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01081081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5416","last_page":"5425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8407999873161316,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8407999873161316,"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/generalization","display_name":"Generalization","score":0.5799999833106995},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4715999960899353},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.44510000944137573},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4422999918460846},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4230000078678131},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.4221999943256378},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4115999937057495},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.40709999203681946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491000294685364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5856000185012817},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4230000078678131},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.4221999943256378},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.40709999203681946},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.3684000074863434},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3476000130176544},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33169999718666077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.17374","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.17374","pdf_url":"https://arxiv.org/pdf/2509.17374","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.17374","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.17374","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.17374","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.17374","pdf_url":"https://arxiv.org/pdf/2509.17374","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"vision\u2013language":[1],"pre-training":[2],"has":[3],"recently":[4],"shown":[5],"promise":[6],"for":[7,45,88,130,136],"no-reference":[8],"image-quality":[9],"assessment":[10,96],"(NR-IQA),":[11,53],"yet":[12],"the":[13,29,46,77,90,128,134,153],"relative":[14],"merits":[15],"of":[16,33,48,79,93],"modern":[17],"Vision":[18],"Transformer":[19],"foundations":[20],"remain":[21],"poorly":[22],"understood.":[23],"In":[24],"this":[25,116],"work,":[26],"we":[27,99,118],"present":[28],"first":[30],"systematic":[31],"evaluation":[32],"six":[34],"prominent":[35],"pretrained":[36],"backbones,":[37],"CLIP,":[38],"SigLIP2,":[39],"DINOv2,":[40],"DINOv3,":[41],"Perception,":[42],"and":[43,75,109,140,148,157],"ResNet,":[44],"task":[47],"No-Reference":[49],"Image":[50],"Quality":[51],"Assessment":[52],"each":[54,131],"fine-tuned":[55],"using":[56],"an":[57],"identical":[58],"lightweight":[59],"MLP":[60],"head.":[61],"Our":[62],"study":[63],"uncovers":[64],"two":[65],"previously":[66],"overlooked":[67],"factors:":[68],"(1)":[69],"SigLIP2":[70],"consistently":[71],"achieves":[72],"strong":[73],"performance;":[74],"(2)":[76],"choice":[78],"activation":[80,122,138],"function":[81],"plays":[82],"a":[83,120],"surprisingly":[84],"crucial":[85],"role,":[86],"particularly":[87],"enhancing":[89],"generalization":[91],"ability":[92],"image":[94],"quality":[95],"models.":[97],"Notably,":[98],"find":[100],"that":[101,125],"simple":[102],"sigmoid":[103],"activations":[104],"outperform":[105],"commonly":[106],"used":[107],"ReLU":[108],"GELU":[110],"on":[111,145],"several":[112],"benchmarks.":[113],"Motivated":[114],"by":[115],"finding,":[117],"introduce":[119],"learnable":[121],"selection":[123],"mechanism":[124],"adaptively":[126],"determines":[127],"nonlinearity":[129],"channel,":[132],"eliminating":[133],"need":[135],"manual":[137],"design,":[139],"achieving":[141],"new":[142],"state-of-the-art":[143],"SRCC":[144],"CLIVE,":[146],"KADID10K,":[147],"AGIQA3K.":[149],"Extensive":[150],"ablations":[151],"confirm":[152],"benefits":[154],"across":[155],"architectures":[156],"regimes,":[158],"establishing":[159],"strong,":[160],"resource-efficient":[161],"NR-IQA":[162],"baselines.":[163],"Code":[164],"is":[165],"available":[166],"at":[167],"https://github.com/drkkgy/NR_IQA_AGM":[168]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-16T00:00:00"}