{"id":"https://openalex.org/W4415707688","doi":"https://doi.org/10.1109/icme59968.2025.11209391","title":"Text-to-Image Diffusion Models are AI-Generated Image Quality Scorers","display_name":"Text-to-Image Diffusion Models are AI-Generated Image Quality Scorers","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707688","doi":"https://doi.org/10.1109/icme59968.2025.11209391"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5044278717","display_name":"Xiangfei Sheng","orcid":"https://orcid.org/0009-0004-8468-1970"},"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":true,"raw_author_name":"Xiangfei Sheng","raw_affiliation_strings":["Xidian University,School of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Artificial Intelligence","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111723399","display_name":"Zou Wei-Dong","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":"Weidong Zou","raw_affiliation_strings":["Xidian University,School of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Artificial Intelligence","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100335055","display_name":"Pengfei Chen","orcid":"https://orcid.org/0000-0002-8042-6831"},"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":"Pengfei Chen","raw_affiliation_strings":["Xidian University,School of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Artificial Intelligence","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767105","display_name":"Li Cai","orcid":"https://orcid.org/0000-0002-8040-5766"},"institutions":[{"id":"https://openalex.org/I50180762","display_name":"Chongqing Three Gorges University","ror":"https://ror.org/05rs3pv16","country_code":"CN","type":"education","lineage":["https://openalex.org/I50180762"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Cai","raw_affiliation_strings":["Chongqing Three Gorges University,School of Electronic and Information Engineering"],"affiliations":[{"raw_affiliation_string":"Chongqing Three Gorges University,School of Electronic and Information Engineering","institution_ids":["https://openalex.org/I50180762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008883063","display_name":"Chao He","orcid":"https://orcid.org/0000-0001-9725-3474"},"institutions":[{"id":"https://openalex.org/I50180762","display_name":"Chongqing Three Gorges University","ror":"https://ror.org/05rs3pv16","country_code":"CN","type":"education","lineage":["https://openalex.org/I50180762"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao He","raw_affiliation_strings":["Chongqing Three Gorges University,School of Electronic and Information Engineering"],"affiliations":[{"raw_affiliation_string":"Chongqing Three Gorges University,School of Electronic and Information Engineering","institution_ids":["https://openalex.org/I50180762"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033615240","display_name":"Leida Li","orcid":"https://orcid.org/0000-0001-9069-8796"},"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":"Leida Li","raw_affiliation_strings":["Xidian University,School of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Artificial Intelligence","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5044278717"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33602443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7408999800682068,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7408999800682068,"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":0.07580000162124634,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.020400000736117363,"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/discriminative-model","display_name":"Discriminative model","score":0.7358999848365784},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6310999989509583},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.553600013256073},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.48890000581741333},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46650001406669617},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.45159998536109924},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.4320000112056732}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7358999848365784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6675999760627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.635699987411499},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6310999989509583},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.553600013256073},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.48890000581741333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.4320000112056732},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4146000146865845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3921000063419342},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3774999976158142},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33629998564720154},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3174000084400177},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2051596736","https://openalex.org/W2194775991","https://openalex.org/W2905544033","https://openalex.org/W3035719652","https://openalex.org/W4312933868","https://openalex.org/W4360884927","https://openalex.org/W4382462760","https://openalex.org/W4386211581","https://openalex.org/W4387010079","https://openalex.org/W4387969352","https://openalex.org/W4390873054","https://openalex.org/W4390874002","https://openalex.org/W4396818947","https://openalex.org/W4402754104","https://openalex.org/W4402904322","https://openalex.org/W4402915913","https://openalex.org/W4402916469","https://openalex.org/W4402951668","https://openalex.org/W4402978319","https://openalex.org/W4402979192","https://openalex.org/W4403791462","https://openalex.org/W4404533930"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,108,125,139],"remarkable":[2],"progress":[3],"in":[4],"text-to-image":[5],"generation":[6],"models,":[7,36,42,91],"AI-Generated":[8,24],"Images":[9],"(AGIs)":[10],"still":[11],"face":[12],"significant":[13],"challenges,":[14],"such":[15],"as":[16],"poor":[17],"perception":[18],"quality":[19,56],"and":[20,57,114,135],"text-image":[21,46,58],"misalignment.":[22],"Consequently,":[23],"Image":[25],"Quality":[26],"Assessment":[27],"(AGIQA),":[28],"which":[29,60],"aims":[30],"to":[31,86,118,145],"assess":[32],"capabilities":[33],"of":[34,79,141],"generative":[35,47],"has":[37],"gained":[38],"increasing":[39],"attention.":[40],"Diffusion":[41],"pre-trained":[43,89],"on":[44,100,131],"large-scale":[45],"tasks,":[48],"inherently":[49],"encode":[50],"rich":[51],"prior":[52],"knowledge":[53],"regarding":[54],"image":[55],"alignment,":[59],"is":[61,149],"crucial":[62],"for":[63],"AGIQA":[64,146],"task.":[65,147],"Inspired":[66],"by":[67],"this,":[68],"unlike":[69],"most":[70],"existing":[71],"CLIP-based":[72],"methods,":[73],"we":[74,92],"present":[75],"an":[76],"initial":[77],"exploration":[78],"diffusion":[80,90,112,126,143],"model-based":[81],"AGIQA,":[82],"termed":[83],"Diff-AGIQA.":[84],"Specifically,":[85],"effectively":[87],"harness":[88],"introduce":[93],"a":[94],"simple":[95],"yet":[96],"effective":[97],"strategy":[98],"focusing":[99],"two":[101],"key":[102],"aspects:":[103],"1)":[104],"feature":[105],"selection,":[106],"identifying":[107],"discriminative":[109],"features":[110,122],"within":[111],"models;":[113],"2)":[115],"visual":[116],"prompting,":[117],"extract":[119],"more":[120],"task-specific":[121],"while":[123],"keeping":[124],"model":[127],"frozen.":[128],"Extensive":[129],"experiments":[130],"AGIQA-1K,":[132],"AGIQA-3K,":[133],"AGIQA-20K,":[134],"RichHF-18K":[136],"datasets":[137],"demonstrate":[138],"potential":[140],"applying":[142],"models":[144],"Code":[148],"publicly":[150],"available":[151],"https://github.com/sxfly99/Diff-AGIQA.":[152]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}