{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T21:05:04Z","timestamp":1784581504537,"version":"3.55.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["MOE-T2EP20123-0006"],"award-info":[{"award-number":["MOE-T2EP20123-0006"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3668530","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:50:03Z","timestamp":1772225403000},"page":"5592-5602","source":"Crossref","is-referenced-by-count":1,"title":["Prompt-Image-Caption Consistency for AI-Generated Image Quality Assessment"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3920-3940","authenticated-orcid":false,"given":"Wen","family":"Sun","sequence":"first","affiliation":[{"name":"College of Computing and Data Science (CCDS), Nanyang Technological University (NTU), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6137-5162","authenticated-orcid":false,"given":"Chaofeng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Liao","sequence":"additional","affiliation":[{"name":"Hangzhou Institute of Technology, Xidian University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9866-1947","authenticated-orcid":false,"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science (CCDS), Nanyang Technological University (NTU), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Text-to-image diffusion models in generative AI: A survey","author":"Zhang","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3399075"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410672"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2011.01.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3325719"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3121875"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2788206"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405729"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3233244"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00636"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3311646"},{"key":"ref17","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref18","article-title":"GIT: A generative image-to-text transformer for vision and language","volume":"2022","author":"Wang","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref20","article-title":"EMU: Generative pretraining in multimodality","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sun","year":"2024"},{"key":"ref21","article-title":"No-reference quality assessment of contrast-distorted images using contrast enhancement","author":"Yan","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2018.2816783"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2355716"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713945"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref28","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref29","first-page":"2226","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref31","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","article-title":"EVA-CLIP: Improved training techniques for CLIP at scale","author":"Sun","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00960"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00637"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3270621"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00644"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00663"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/QOMEX.2009.5246972"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2014.2344471"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref47","article-title":"dreamlike-photoreal-2.0","year":"2023"},{"key":"ref48","article-title":"Midjourney","author":"Holz","year":"2023"},{"key":"ref49","article-title":"LCM-LoRA: A universal stable-diffusion acceleration module","author":"Luo","year":"2023"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11417244.pdf?arnumber=11417244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T20:20:43Z","timestamp":1784578843000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11417244\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3668530","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}