{"id":"https://openalex.org/W7131854188","doi":"https://doi.org/10.1109/tmm.2026.3668530","title":"Prompt-Image-Caption Consistency for AI-Generated Image Quality Assessment","display_name":"Prompt-Image-Caption Consistency for AI-Generated Image Quality Assessment","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131854188","doi":"https://doi.org/10.1109/tmm.2026.3668530"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2026.3668530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668530","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","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/A5127272526","display_name":"Wen Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wen Sun","raw_affiliation_strings":["College of Computing and Data Science (CCDS), Nanyang Technological University (NTU), Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3920-3940","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science (CCDS), Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127120988","display_name":"Chaofeng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaofeng Chen","raw_affiliation_strings":["School of Artificial Intelligence, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6137-5162","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127112802","display_name":"Liang Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Liao","raw_affiliation_strings":["Hangzhou Institute of Technology, Xidian University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Institute of Technology, Xidian University, Hangzhou, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105619861","display_name":"W. N. Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weisi Lin","raw_affiliation_strings":["College of Computing and Data Science (CCDS), Nanyang Technological University (NTU), Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9866-1947","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science (CCDS), Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7614,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94919151,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"5592","last_page":"5602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9524000287055969,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9524000287055969,"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":0.013500000350177288,"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":0.005400000140070915,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.7919999957084656},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6326000094413757},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5892000198364258},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5724999904632568},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5544999837875366},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.5393999814987183},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5026999711990356},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5019000172615051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101999759674072},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7919999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6349999904632568},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6326000094413757},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5892000198364258},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5724999904632568},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.5393999814987183},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5019000172615051},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4406999945640564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42480000853538513},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4050000011920929},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.3684999942779541},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35690000653266907},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.33889999985694885},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2750000059604645}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2026.3668530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668530","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/212163","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/212163","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1849107595","display_name":null,"funder_award_id":"MOE- T2EP20123-0006","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,20,33,49,116,123,146,149,186],"advancement":[2],"of":[3,35,51,77],"generative":[4,6],"AI,":[5],"models":[7,16],"such":[8],"as":[9],"Generative":[10],"Adversarial":[11],"Networks":[12],"(GANs)":[13],"and":[14,48,65,69,81,112,130,140,152,164,182],"diffusion-based":[15],"have":[17],"significantly":[18],"enhanced":[19],"capabilities":[21],"in":[22,29,40,75],"generating":[23],"photorealistic":[24],"images.":[25],"Despite":[26],"significant":[27],"progress":[28],"AI-Generated":[30],"Images":[31],"(AIGIs),":[32],"evaluation":[34],"AIGI":[36,72,103],"quality":[37,73,80,104,111],"remains":[38],"underexplored":[39],"multiple":[41,168],"aspects,":[42],"including":[43,180],"AI":[44],"artifacts,":[45],"unnatural":[46],"content,":[47],"availability":[50],"input":[52],"text":[53,70],"prompts.":[54],"However,":[55],"existing":[56],"methods":[57],"are":[58],"insufficient":[59],"to":[60,96,136,144,160,193],"capture":[61,137],"both":[62,108,162],"feature":[63],"representations":[64],"correlations":[66,147],"between":[67],"image":[68,79,110,128],"for":[71,102],"assessment":[74,105],"aspects":[76],"perceptual":[78,109],"text-to-image":[82,113],"alignment.":[83],"To":[84],"address":[85],"this,":[86],"we":[87,155],"proposed":[88,187],"a":[89,98,157],"novel":[90],"Prompt-Image-Caption":[91],"Consistency":[92],"(PICC)":[93],"framework,":[94],"designed":[95],"adapt":[97],"pre-trained":[99],"vision-language":[100],"model":[101],"by":[106,126],"considering":[107],"alignment":[114],"at":[115],"same":[117],"time.":[118],"This":[119],"framework":[120],"effectively":[121],"explores":[122],"prompt-image-caption":[124,169],"triplet":[125],"adapting":[127],"embedding":[129,132],"multimodal":[131],"via":[133],"Quality-Aware":[134],"Attention":[135],"quality-aware":[138],"features":[139],"calculating":[141],"consistency":[142],"scores":[143],"build":[145],"among":[148],"prompt,":[150],"image,":[151],"caption.":[153],"Additionally,":[154],"propose":[156],"multilevel":[158],"strategy":[159],"integrate":[161],"local":[163],"global":[165],"information":[166],"from":[167],"triplets,":[170],"further":[171],"enhancing":[172],"prediction":[173],"performance.":[174],"Extensive":[175],"experiments":[176],"on":[177],"benchmark":[178],"datasets,":[179],"AIGIQA-20K":[181],"AGIQA-3K,":[183],"demonstrate":[184],"that":[185],"PICC":[188],"achieves":[189],"state-of-the-art":[190],"performance":[191],"compared":[192],"baseline":[194],"methods.":[195],"The":[196],"code":[197],"will":[198],"be":[199],"made":[200],"publicly":[201],"available.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-02-28T00:00:00"}