{"id":"https://openalex.org/W4417168932","doi":"https://doi.org/10.1109/tip.2025.3639998","title":"Enhancing Descriptive Image Quality Assessment With a Large-Scale Multi-Modal Dataset","display_name":"Enhancing Descriptive Image Quality Assessment With a Large-Scale Multi-Modal Dataset","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4417168932","doi":"https://doi.org/10.1109/tip.2025.3639998","pmid":"https://pubmed.ncbi.nlm.nih.gov/41364577"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3639998","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tip.2025.3639998","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tip.2025.3639998","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113315332","display_name":"Zhiyuan You","orcid":"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":true,"raw_author_name":"Zhiyuan You","raw_affiliation_strings":["Multimedia Laboratory, The Chinese University of Hong Kong, Hong Kong, China","The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Multimedia Laboratory, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078100073","display_name":"Jinjin Gu","orcid":"https://orcid.org/0000-0002-4389-6236"},"institutions":[{"id":"https://openalex.org/I58918642","display_name":"Sofia University \"St. Kliment Ohridski\"","ror":"https://ror.org/02jv3k292","country_code":"BG","type":"education","lineage":["https://openalex.org/I58918642"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Jinjin Gu","raw_affiliation_strings":["INSAIT, Sofia University “St. Kliment Ohridski”,, Sofia, Bulgaria","INSAIT, Sofia University, Sofia, Bulgaria"],"affiliations":[{"raw_affiliation_string":"INSAIT, Sofia University “St. Kliment Ohridski”,, Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]},{"raw_affiliation_string":"INSAIT, Sofia University, Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119272181","display_name":"Xin Cai","orcid":"https://orcid.org/0009-0005-9121-6900"},"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":"Xin Cai","raw_affiliation_strings":["Multimedia Laboratory, The Chinese University of Hong Kong, Hong Kong, China","The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Multimedia Laboratory, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103160307","display_name":"Zheyuan Li","orcid":"https://orcid.org/0000-0002-7434-5947"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheyuan Li","raw_affiliation_strings":["Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaiwen Zhu","orcid":"https://orcid.org/0009-0002-5195-5707"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiwen Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023845728","display_name":"Chao Dong","orcid":"https://orcid.org/0000-0003-2260-8079"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Dong","raw_affiliation_strings":["Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100552155","display_name":"Tianfan Xue","orcid":"https://orcid.org/0000-0001-5031-6618"},"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"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Tianfan Xue","raw_affiliation_strings":["Multimedia Laboratory, The Chinese University of Hong Kong, Hong Kong, China","Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Multimedia Laboratory, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113315332"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85699922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"34","issue":null,"first_page":"8201","last_page":"8215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.3133000135421753,"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":0.3133000135421753,"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":0.2727000117301941,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.06679999828338623,"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/image-quality","display_name":"Image quality","score":0.6284000277519226},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5902000069618225},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5357000231742859},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5224999785423279},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5097000002861023},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5041999816894531},{"id":"https://openalex.org/keywords/quality-score","display_name":"Quality Score","score":0.4948999881744385},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45350000262260437},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4422999918460846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8119999766349792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6294000148773193},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.6284000277519226},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5902000069618225},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5357000231742859},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5097000002861023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5088000297546387},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.4948999881744385},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44519999623298645},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3644999861717224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3224000036716461},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31189998984336853},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.31119999289512634},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3041999936103821},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3639998","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tip.2025.3639998","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41364577","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41364577","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tip.2025.3639998","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tip.2025.3639998","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1484410455","display_name":null,"funder_award_id":"62276251","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G504125008","display_name":null,"funder_award_id":"Grant No.62276251","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W104847522","https://openalex.org/W1974013408","https://openalex.org/W1981572319","https://openalex.org/W1982471090","https://openalex.org/W2007522261","https://openalex.org/W2042230566","https://openalex.org/W2046119925","https://openalex.org/W2051596736","https://openalex.org/W2102166818","https://openalex.org/W2129644086","https://openalex.org/W2133665775","https://openalex.org/W2141983208","https://openalex.org/W2162692770","https://openalex.org/W2163370434","https://openalex.org/W2185175083","https://openalex.org/W2245625259","https://openalex.org/W2500825094","https://openalex.org/W2546855109","https://openalex.org/W2560730294","https://openalex.org/W2563786098","https://openalex.org/W2565312867","https://openalex.org/W2606974598","https://openalex.org/W2783836469","https://openalex.org/W2798581339","https://openalex.org/W2904565150","https://openalex.org/W2953590133","https://openalex.org/W2962785568","https://openalex.org/W2963250244","https://openalex.org/W2963796134","https://openalex.org/W2963975576","https://openalex.org/W2970641574","https://openalex.org/W2979382951","https://openalex.org/W2981731882","https://openalex.org/W3002992380","https://openalex.org/W3004352908","https://openalex.org/W3017136408","https://openalex.org/W3034882073","https://openalex.org/W3035595647","https://openalex.org/W3035719652","https://openalex.org/W3047237378","https://openalex.org/W3048549109","https://openalex.org/W3120043490","https://openalex.org/W3130885914","https://openalex.org/W3135955502","https://openalex.org/W3170697543","https://openalex.org/W3173787059","https://openalex.org/W3174970555","https://openalex.org/W3176196997","https://openalex.org/W3193517049","https://openalex.org/W3205575841","https://openalex.org/W3207918547","https://openalex.org/W4214609808","https://openalex.org/W4214745154","https://openalex.org/W4221144351","https://openalex.org/W4224267514","https://openalex.org/W4225672218","https://openalex.org/W4285255856","https://openalex.org/W4304084118","https://openalex.org/W4312286465","https://openalex.org/W4312432424","https://openalex.org/W4312678820","https://openalex.org/W4312968447","https://openalex.org/W4319300090","https://openalex.org/W4382462760","https://openalex.org/W4385245566","https://openalex.org/W4386076169","https://openalex.org/W4386083034","https://openalex.org/W4390874566","https://openalex.org/W4401070165","https://openalex.org/W4402671653","https://openalex.org/W4402704606","https://openalex.org/W4402727669","https://openalex.org/W4402951581","https://openalex.org/W4403081466","https://openalex.org/W4403844348","https://openalex.org/W4403942500","https://openalex.org/W4404536559","https://openalex.org/W4404613040","https://openalex.org/W4413145151","https://openalex.org/W4414281281"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,27,80,125,130,206],"rapid":[2],"advancement":[3],"of":[4,30],"Vision":[5],"Language":[6],"Models":[7],"(VLMs),":[8],"VLM-based":[9,182],"Image":[10],"Quality":[11,84],"Assessment":[12,85],"(IQA)":[13],"seeks":[14],"to":[15,20,66,118,127,152,166],"describe":[16],"image":[17,83,148],"quality":[18,156],"linguistically":[19],"align":[21,55],"with":[22,56],"human":[23],"expression":[24],"and":[25,72,100,104,108,122,140,158,185,193,209,215],"capture":[26],"multifaceted":[28],"nature":[29],"IQA":[31,93,183],"tasks.":[32,195],"However,":[33],"current":[34],"methods":[35],"are":[36,198],"still":[37],"far":[38],"from":[39],"practical":[40],"usage.":[41],"First,":[42],"prior":[43,181],"works":[44],"focus":[45],"narrowly":[46],"on":[47],"specific":[48],"sub-tasks":[49],"or":[50],"settings,":[51],"which":[52],"do":[53],"not":[54],"diverse":[57],"real-world":[58,202],"applications.":[59],"Second,":[60],"their":[61],"performance":[62],"is":[63,164],"sub-optimal":[64],"due":[65],"limitations":[67],"in":[68,188,221],"dataset":[69,115,126],"coverage,":[70],"scale,":[71],"quality.":[73],"To":[74],"overcome":[75],"these":[76],"challenges,":[77],"we":[78,135],"introduce":[79,112],"Enhanced":[81],"Depicted":[82],"model":[86,216],"(EDQA).":[87],"Our":[88,196],"method":[89],"includes":[90],"a":[91,113,137,160],"multi-functional":[92],"task":[94],"paradigm":[95],"that":[96,163,174],"encompasses":[97],"both":[98],"assessment":[99],"comparison":[101],"tasks,":[102],"brief":[103],"detailed":[105],"responses,":[106],"full-reference":[107],"non-reference":[109],"scenarios.":[110],"We":[111,145],"ground-truth-informed":[114],"construction":[116],"approach":[117],"enhance":[119],"data":[120],"quality,":[121],"scale":[123],"up":[124],"495K":[128],"under":[129],"brief-detail":[131],"joint":[132],"framework.":[133],"Consequently,":[134],"construct":[136],"comprehensive,":[138],"large-scale,":[139],"high-quality":[141],"dataset,":[142],"named":[143],"EDQA-495K.":[144],"also":[146],"retain":[147],"resolution":[149],"during":[150],"training":[151],"better":[153],"handle":[154],"resolution-related":[155],"issues,":[157],"estimate":[159],"confidence":[161],"score":[162],"helpful":[165],"filter":[167],"out":[168],"low-quality":[169],"responses.":[170],"Experimental":[171],"results":[172],"demonstrate":[173],"EDQA":[175],"significantly":[176],"outperforms":[177],"traditional":[178],"score-based":[179],"methods,":[180],"models,":[184],"proprietary":[186],"GPT-4V":[187],"distortion":[189],"identification,":[190],"instant":[191],"rating,":[192],"reasoning":[194],"advantages":[197],"further":[199],"confirmed":[200],"by":[201],"applications":[203],"including":[204],"assessing":[205],"web-downloaded":[207],"images":[208],"ranking":[210],"model-processed":[211],"images.":[212],"Codes,":[213],"datasets,":[214],"weights":[217],"have":[218],"been":[219],"released":[220],"https://depictqa.github.io/.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-09T00:00:00"}