{"id":"https://openalex.org/W4407212562","doi":"https://doi.org/10.1109/mmul.2025.3538862","title":"Quality Assessment for Text-to-Image Generation: A Survey","display_name":"Quality Assessment for Text-to-Image Generation: A Survey","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407212562","doi":"https://doi.org/10.1109/mmul.2025.3538862"},"language":"en","primary_location":{"id":"doi:10.1109/mmul.2025.3538862","is_oa":true,"landing_page_url":"https://doi.org/10.1109/mmul.2025.3538862","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 MultiMedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/mmul.2025.3538862","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100745438","display_name":"Yu Tian","orcid":"https://orcid.org/0000-0002-8147-8334"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yu Tian","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8147-8334","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320064","display_name":"Yue Liu","orcid":"https://orcid.org/0000-0002-3196-6866"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yue Liu","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3196-6866","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385178","display_name":"Shiqi Wang","orcid":"https://orcid.org/0000-0002-3583-959X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shiqi Wang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3583-959X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008386708","display_name":"Sam Kwong","orcid":"https://orcid.org/0000-0001-7484-7261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Kwong","raw_affiliation_strings":["Lingnan University, Hong Kong, SAR, China","Lingnan Univeirsty, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-7484-7261","affiliations":[{"raw_affiliation_string":"Lingnan University, Hong Kong, SAR, China","institution_ids":[]},{"raw_affiliation_string":"Lingnan Univeirsty, Hong Kong, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5932,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.94535272,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"32","issue":"2","first_page":"44","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9050999879837036,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9050999879837036,"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":0.7944449186325073},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.497651606798172},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4662111699581146},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4486812651157379},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4002808928489685},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37666746973991394},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37402409315109253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35862085223197937},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33734530210494995},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.32423704862594604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7944449186325073},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.497651606798172},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4662111699581146},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4486812651157379},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4002808928489685},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37666746973991394},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37402409315109253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35862085223197937},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33734530210494995},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.32423704862594604},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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":2,"locations":[{"id":"doi:10.1109/mmul.2025.3538862","is_oa":true,"landing_page_url":"https://doi.org/10.1109/mmul.2025.3538862","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 MultiMedia","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/6c376022-9fa4-455f-a323-4d7817c1ad64","is_oa":true,"landing_page_url":"https://hdl.handle.net/2031/6c376022-9fa4-455f-a323-4d7817c1ad64","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Tian, Y, Liu, Y, Wang, S & Kwong, S 2025, 'Quality Assessment for Text-to-Image Generation : A Survey', IEEE MultiMedia, vol. 32, no. 2, pp. 44-52. https://doi.org/10.1109/MMUL.2025.3538862","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/mmul.2025.3538862","is_oa":true,"landing_page_url":"https://doi.org/10.1109/mmul.2025.3538862","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 MultiMedia","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7216417609","display_name":null,"funder_award_id":"2018AAA0101301","funder_id":"https://openalex.org/F4320324196","funder_display_name":"Innovation and Technology Commission - Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320324196","display_name":"Innovation and Technology Commission - Hong Kong","ror":"https://ror.org/04vf9tr09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2153156486","https://openalex.org/W3108650314","https://openalex.org/W3134293987","https://openalex.org/W3153469116","https://openalex.org/W4387010079","https://openalex.org/W4389519077","https://openalex.org/W4390874002","https://openalex.org/W4399381390","https://openalex.org/W4402904202","https://openalex.org/W4402915913","https://openalex.org/W4403791804"],"related_works":["https://openalex.org/W304855073","https://openalex.org/W372519479","https://openalex.org/W938111471","https://openalex.org/W2511882081","https://openalex.org/W2356683864","https://openalex.org/W2518250394","https://openalex.org/W2032169142","https://openalex.org/W2267221041","https://openalex.org/W98823754","https://openalex.org/W2384667405"],"abstract_inverted_index":{"In":[0,82],"recent":[1,73],"years,":[2],"there":[3],"have":[4,41],"been":[5],"notable":[6],"advancements":[7,74],"in":[8,75],"text-to-image":[9,80],"generation":[10,18],"facilitated":[11],"by":[12],"artificial":[13],"intelligence":[14],"(AI)":[15],"technology.":[16],"Text-to-image":[17],"requires":[19],"higher-level":[20],"cognitive":[21],"abilities,":[22],"posing":[23],"unique":[24],"challenges":[25],"for":[26,32,79,101],"image":[27,76,107],"quality":[28,44,77,87],"assessment":[29,45,78,88],"typically":[30],"designed":[31],"professionally":[33],"generated":[34],"content":[35],"and":[36,48,64,92,98,117],"user-generated":[37],"content.":[38],"Existing":[39],"works":[40],"extensively":[42],"investigated":[43],"from":[46,90],"subjective":[47,91],"objective":[49,93,99],"perspectives,":[50,94],"covering":[51],"a":[52,69],"range":[53],"of":[54,72,105,114],"evaluation":[55],"dimensions":[56],"such":[57],"as":[58],"text\u2013image":[59],"alignment,":[60],"perception,":[61],"esthetics,":[62],"fairness,":[63],"toxicity.":[65],"This":[66],"article":[67],"provides":[68],"comprehensive":[70],"overview":[71],"generation.":[81],"particular,":[83],"we":[84,110],"review":[85],"existing":[86],"studies":[89],"highlighting":[95],"representative":[96],"datasets":[97],"metrics":[100],"assessing":[102],"different":[103],"aspects":[104],"AI-generated":[106],"quality.":[108],"Additionally,":[109],"discuss":[111],"the":[112],"limitations":[113],"current":[115],"research":[116],"propose":[118],"future":[119],"directions.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
