{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T23:38:40Z","timestamp":1769557120116,"version":"3.49.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271323"],"award-info":[{"award-number":["62271323"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2035"],"award-info":[{"award-number":["U22B2035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515012956"],"award-info":[{"award-number":["2023A1515012956"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023B1212060076"],"award-info":[{"award-number":["2023B1212060076"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017622","name":"Shenzhen Research and Development Program","doi-asserted-by":"publisher","award":["JCYJ20220531102408020"],"award-info":[{"award-number":["JCYJ20220531102408020"]}],"id":[{"id":"10.13039\/501100017622","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017622","name":"Shenzhen Research and Development Program","doi-asserted-by":"publisher","award":["KJZD20230923114209019"],"award-info":[{"award-number":["KJZD20230923114209019"]}],"id":[{"id":"10.13039\/501100017622","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/jstsp.2024.3516392","type":"journal-article","created":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T19:14:05Z","timestamp":1734030845000},"page":"234-247","source":"Crossref","is-referenced-by-count":1,"title":["Vision Language Modeling of Content, Distortion and Appearance for Image Quality Assessment"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1216-2181","authenticated-orcid":false,"given":"Fei","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Electronic and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4230-2421","authenticated-orcid":false,"given":"Tianhao","family":"Gu","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicong","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5877-5648","authenticated-orcid":false,"given":"Guoping","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/188"},{"key":"ref4","article-title":"Deep neural networks for blind image quality assessment: Addressing the data challenge","author":"Athar","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378466"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2760518"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01415"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3270621"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3275376"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"issue":"8","key":"ref16","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00010"},{"key":"ref18","first-page":"9216","article-title":"An image is worth more than a thousand words: Towards disentanglement in the wild","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Gabbay","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01769"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00939"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref26","first-page":"1008","article-title":"UniCLIP: Unified framework for contrastive language-image pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lee","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3299328"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181496"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00566"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3145326"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02136"},{"key":"ref36","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016464"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref39","article-title":"Deepfl-IQA: Weak supervision for deep iqa feature learning","author":"Lin","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025113"},{"key":"ref45","article-title":"Clipcap: CLIP prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2199980"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1117\/12.477378"},{"key":"ref48","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref49","first-page":"46595","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zheng","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"},{"issue":"1","key":"ref51","doi-asserted-by":"crossref","first-page":"11006","DOI":"10.1117\/1.3267105","article-title":"Most apparent distortion: Full-reference image quality assessment and the role of strategy","volume":"19","author":"Larson","year":"2010","journal-title":"J. Electron. Imag."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2014.10.009"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247789"},{"key":"ref59","article-title":"A probabilistic quality representation approach to deep blind image quality prediction","author":"Zeng","year":"2017"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3196815"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3578584"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2898638"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301276"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02408"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/10906680\/10795128.pdf?arnumber=10795128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T17:44:21Z","timestamp":1749663861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10795128\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":65,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2024.3516392","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}