{"id":"https://openalex.org/W4405304514","doi":"https://doi.org/10.1109/jstsp.2024.3516392","title":"Vision Language Modeling of Content, Distortion and Appearance for Image Quality Assessment","display_name":"Vision Language Modeling of Content, Distortion and Appearance for Image Quality Assessment","publication_year":2024,"publication_date":"2024-12-12","ids":{"openalex":"https://openalex.org/W4405304514","doi":"https://doi.org/10.1109/jstsp.2024.3516392"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2024.3516392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2024.3516392","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","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/A5090831580","display_name":"Fei Zhou","orcid":"https://orcid.org/0000-0003-1216-2181"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fei Zhou","raw_affiliation_strings":["College of Electronic and Information Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1216-2181","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianhao Gu","orcid":"https://orcid.org/0009-0002-4230-2421"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Gu","raw_affiliation_strings":["College of Electronic and Information Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-4230-2421","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113156921","display_name":"Zhicong Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicong Huang","raw_affiliation_strings":["College of Electronic and Information Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114259459","display_name":"Guoping Qiu","orcid":"https://orcid.org/0000-0002-5877-5648"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoping Qiu","raw_affiliation_strings":["School of Computer Science, University of Nottingham Ningbo China, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-5877-5648","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Nottingham Ningbo China, Zhejiang, China","institution_ids":["https://openalex.org/I13591777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090831580"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55511475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"19","issue":"1","first_page":"234","last_page":"247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9896000027656555,"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":0.9876000285148621,"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/computer-science","display_name":"Computer science","score":0.6572415828704834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6256422996520996},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5861395597457886},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.5753764510154724},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5733460187911987},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5277396440505981},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5187859535217285},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.423534631729126},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40081578493118286},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3387565314769745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18657469749450684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6572415828704834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6256422996520996},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5861395597457886},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.5753764510154724},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5733460187911987},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5277396440505981},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5187859535217285},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.423534631729126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40081578493118286},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3387565314769745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18657469749450684},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2024.3516392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2024.3516392","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4623173173","display_name":null,"funder_award_id":"62271323","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4978424058","display_name":null,"funder_award_id":"JCYJ20220531102408020","funder_id":"https://openalex.org/F4320329801","funder_display_name":"Shenzhen Research and Development Program"},{"id":"https://openalex.org/G5392543476","display_name":null,"funder_award_id":"2023A1515012956","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G5430980299","display_name":null,"funder_award_id":"U22B2035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7058737390","display_name":null,"funder_award_id":"KJZD20230923114209019","funder_id":"https://openalex.org/F4320329801","funder_display_name":"Shenzhen Research and Development Program"},{"id":"https://openalex.org/G7629561560","display_name":null,"funder_award_id":"2023B1212060076","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329801","display_name":"Shenzhen Research and Development Program","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1974013408","https://openalex.org/W1982471090","https://openalex.org/W1984066865","https://openalex.org/W1987489060","https://openalex.org/W1996667837","https://openalex.org/W2031489346","https://openalex.org/W2078807908","https://openalex.org/W2102166818","https://openalex.org/W2108598243","https://openalex.org/W2148848374","https://openalex.org/W2161907179","https://openalex.org/W2171349048","https://openalex.org/W2245625259","https://openalex.org/W2563786098","https://openalex.org/W2732026016","https://openalex.org/W2752223497","https://openalex.org/W2905544033","https://openalex.org/W2912610845","https://openalex.org/W2953590133","https://openalex.org/W3000809580","https://openalex.org/W3002992380","https://openalex.org/W3030380536","https://openalex.org/W3034882073","https://openalex.org/W3035524453","https://openalex.org/W3035595647","https://openalex.org/W3035712445","https://openalex.org/W3035719652","https://openalex.org/W3067922556","https://openalex.org/W3091249416","https://openalex.org/W3100404621","https://openalex.org/W3135479537","https://openalex.org/W3153469116","https://openalex.org/W3204462479","https://openalex.org/W3210514413","https://openalex.org/W4210632776","https://openalex.org/W4214745154","https://openalex.org/W4226058394","https://openalex.org/W4281262963","https://openalex.org/W4297808394","https://openalex.org/W4307106676","https://openalex.org/W4312563428","https://openalex.org/W4312599396","https://openalex.org/W4312629998","https://openalex.org/W4312805760","https://openalex.org/W4312877428","https://openalex.org/W4312960937","https://openalex.org/W4313156423","https://openalex.org/W4313641268","https://openalex.org/W4367146870","https://openalex.org/W4376466809","https://openalex.org/W4382462760","https://openalex.org/W4385339047","https://openalex.org/W4385574853","https://openalex.org/W4385767833","https://openalex.org/W4386071514","https://openalex.org/W4386071753","https://openalex.org/W4386076169","https://openalex.org/W4393078930","https://openalex.org/W4394625593","https://openalex.org/W4402704606","https://openalex.org/W6743767099","https://openalex.org/W6772919626","https://openalex.org/W6791353385","https://openalex.org/W6797230115","https://openalex.org/W6802351527","https://openalex.org/W6803567076","https://openalex.org/W6843495165","https://openalex.org/W6844194202","https://openalex.org/W6852874933"],"related_works":["https://openalex.org/W4250539519","https://openalex.org/W4294018197","https://openalex.org/W4233433299","https://openalex.org/W2328889547","https://openalex.org/W2379384513","https://openalex.org/W2213288308","https://openalex.org/W2884856691","https://openalex.org/W4244821991","https://openalex.org/W2125732910","https://openalex.org/W3003858543"],"abstract_inverted_index":{"The":[0,150,179],"visual":[1,100],"quality":[2,37,66,147],"of":[3,11,55,135,146,170,211,217,224],"an":[4],"image":[5,139],"is":[6,40],"confounded":[7],"by":[8],"a":[9,58,79,96,128,133],"number":[10],"intertwined":[12],"factors":[13],"including":[14],"its":[15,136,218,225],"semantic":[16,113,172],"content,":[17],"distortion":[18,115,174],"characteristics":[19,116,175],"and":[20,28,87,99,117,155,176,184,221],"appearance":[21,118,177],"properties":[22,119],"such":[23],"as":[24],"brightness,":[25],"contrast,":[26],"sharpness,":[27],"colourfulness.":[29],"Distilling":[30],"high":[31,107],"level":[32,108],"knowledge":[33,109],"about":[34,110],"all":[35,63,143],"these":[36,56,64],"bearing":[38],"attributes":[39,68],"crucial":[41],"for":[42,105,120,181,192,196],"developing":[43],"objective":[44],"Image":[45,90],"Quality":[46],"Assessment":[47],"(IQA).":[48],"While":[49],"existing":[50],"solutions":[51],"have":[52,126],"modeled":[53],"some":[54],"aspects,":[57],"comprehensive":[59],"solution":[60],"that":[61,94,204],"involves":[62],"important":[65],"related":[67],"has":[69,161,206],"not":[70],"yet":[71],"been":[72],"developed.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77,125],"present":[78],"new":[80],"blind":[81],"IQA":[82,198],"(BIQA)":[83],"model":[84],"termed":[85],"Self-supervision":[86],"Vision-Language":[88],"supervision":[89],"QUality":[91],"Evaluator":[92],"(SLIQUE)":[93],"features":[95],"joint":[97],"vision-language":[98,194],"contrastive":[101],"representation":[102],"learning":[103],"framework":[104],"acquiring":[106],"the":[111,185,212,215,222],"images":[112,165],"contents,":[114,173],"IQA.":[121],"For":[122],"training":[123],"SLIQUE,":[124],"developed":[127],"systematic":[129],"approach":[130],"to":[131],"constructing":[132,182],"first":[134],"kind":[137],"large":[138],"database":[140,160,186],"annotated":[141,166],"with":[142,167],"three":[144],"categories":[145],"relevant":[148],"texts.":[149],"Text":[151],"Annotated":[152],"Distortion,":[153],"Appearance":[154],"Content":[156],"(TADAC<sup":[157],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[158],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>)":[159],"over":[162,209],"1.6":[163],"million":[164],"textual":[168],"descriptions":[169],"their":[171],"properties.":[178],"method":[180],"TADAC":[183],"itself":[187],"will":[188],"be":[189],"particularly":[190],"useful":[191],"exploiting":[193],"modeling":[195],"advanced":[197],"applications.":[199],"Extensive":[200],"experimental":[201],"results":[202],"show":[203],"SLIQUE":[205],"superior":[207],"performances":[208],"state":[210],"art,":[213],"demonstrating":[214],"soundness":[216],"design":[219],"principle":[220],"effectiveness":[223],"implementation.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}