{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:10Z","timestamp":1778048350539,"version":"3.51.4"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00525","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"5416-5425","source":"Crossref","is-referenced-by-count":0,"title":["Revisiting Vision\u2013Language Foundations for No-Reference Image Quality Assessment"],"prefix":"10.1109","author":[{"given":"Ankit","family":"Yadav","sequence":"first","affiliation":[{"name":"The University of Adelaide,Adelaide,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ta Duc","family":"Huy","sequence":"additional","affiliation":[{"name":"The University of Adelaide,Adelaide,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingqiao","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Adelaide,Adelaide,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00026"},{"key":"ref2","article-title":"Perception encoder: The best visual embeddings are not at the output of the network","author":"Bolya","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2760518"},{"key":"ref4","article-title":"Genziqa: Generalized image quality assessment using prompt-guided latent diffusion models","author":"De","year":"2024"},{"key":"ref5","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.06.111"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref8","article-title":"Dp-iqa: Utilizing diffusion prior for blind image quality assessment in the wild","author":"Fu","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00404"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"issue":"2","key":"ref14","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"ref18","article-title":"Deepfl-iqa: Weak supervision for deep iqa feature learning","author":"Lin","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181496"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref21","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00566"},{"key":"ref25","article-title":"LGDM: Latent guidance in diffusion models for perceptual evaluations","volume-title":"Forty-second International Conference on Machine Learning","author":"Saini"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01216"},{"key":"ref27","article-title":"Dinov3","author":"Sim\u00e9oni","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-52243-8_4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78125-4_4"},{"key":"ref32","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025"},{"key":"ref33","article-title":"Regularization and reparameterization avoid vanishing gradients in sigmoid-type networks","author":"Ven","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00257"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506075"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2426416"},{"issue":"35","key":"ref38","first-page":"1","article-title":"Deep network approximation: Beyond relu to diverse activation functions","volume":"25","author":"Zhang","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00082"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02136"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01415"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492248.pdf?arnumber=11492248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:55:38Z","timestamp":1778046938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00525","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}