{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T06:22:52Z","timestamp":1787638972995,"version":"build-2736575974"},"reference-count":58,"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":[{"name":"Research Grant Council (RGC) of Hong Kong General Research Fund","award":["11200323"],"award-info":[{"award-number":["11200323"]}]},{"name":"RGC Research Fellow Scheme","award":["RFS2526-1S04"],"award-info":[{"award-number":["RFS2526-1S04"]}]},{"name":"NSFC\/RGC JRS Project","award":["N_CityU198\/24"],"award-info":[{"award-number":["N_CityU198\/24"]}]},{"name":"ITC","award":["GHP\/044\/21SZ"],"award-info":[{"award-number":["GHP\/044\/21SZ"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3723242","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T19:12:53Z","timestamp":1787080373000},"page":"8966-8979","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Fidelity-Perception Tradeoff via Large Vision\u2013Language Model Prior for Image Compression"],"prefix":"10.1109","volume":"35","author":[{"given":"Yudong","family":"Mao","sequence":"first","affiliation":[{"name":"City University of Hong Kong","place":["Hong Kong, SAR, China"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6636-522X","authenticated-orcid":false,"given":"Peilin","family":"Chen","sequence":"additional","affiliation":[{"name":"City University of Hong Kong","place":["Hong Kong, SAR, China"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7605-5638","authenticated-orcid":false,"given":"Hao","family":"Luo","sequence":"additional","affiliation":[{"name":"City University of Hong Kong","place":["Hong Kong, SAR, China"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7608-7913","authenticated-orcid":false,"given":"Lingyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"City University of Hong Kong","place":["Hong Kong, SAR, China"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0475-3689","authenticated-orcid":false,"given":"Yung-Hui","family":"Li","sequence":"additional","affiliation":[{"name":"Hon Hai Research Institute","place":["New Taipei City, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3583-959X","authenticated-orcid":false,"given":"Shiqi","family":"Wang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong","place":["Hong Kong, SAR, China"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"End-to-end optimized image compression","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Ball\u00e9"},{"key":"ref2","article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Ball"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"ref5","volume-title":"BPG Image Format","author":"Bellard","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2007.916009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2010.2099114"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2014.2352455"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2641456"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3290519"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2835"},{"key":"ref15","article-title":"Extreme generative image compression by learning text embedding from diffusion models","author":"Pan","year":"2022","journal-title":"arXiv:2211.07793"},{"key":"ref16","article-title":"Text+ sketch: Image compression at ultra low rates","volume-title":"Proc. ICML Workshop","author":"Lei"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3455576"},{"key":"ref18","article-title":"Idempotence and perceptual image compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02138"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00288"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref22","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref23","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"},{"key":"ref24","article-title":"Perceptual image compression with cooperative cross-modal side information","author":"Qin","year":"2023","journal-title":"arXiv:2311.13847"},{"key":"ref25","first-page":"26715","article-title":"Neural image compression with text-guided encoding for both pixel-level and perceptual fidelity","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Lee"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25184"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2960869"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00221"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2007.07.001"},{"key":"ref30","first-page":"1","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Minnen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref32","first-page":"11913","article-title":"High-fidelity generative image compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Mentzer"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref34","first-page":"25426","article-title":"Improving statistical fidelity for neural image compression with implicit local likelihood models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Muckley"},{"key":"ref35","article-title":"High-fidelity image compression with score-based generative models","author":"Hoogeboom","year":"2023","journal-title":"arXiv:2305.18231"},{"key":"ref36","article-title":"Correcting diffusion-based perceptual image compression with privileged end-to-end decoder","author":"Ma","year":"2024","journal-title":"arXiv:2404.04916"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00652"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112532"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104222"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00280"},{"key":"ref43","first-page":"675","article-title":"Rethinking lossy compression: The rate-distortion-perception tradeoff","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blau"},{"key":"ref44","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"ref47","article-title":"LoRA-composer: Leveraging low-rank adaptation for multi-concept customization in training-free diffusion models","author":"Yang","year":"2024","journal-title":"arXiv:2403.11627"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref49","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref50","article-title":"Kodak lossless true color image suite","author":"Franzen","year":"1999"},{"key":"ref51","article-title":"CLIC 2020: Challenge on learned image compression","volume-title":"Proc. Workshop Challenge Learned Image Compress. (CLIC)","author":"George","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref54","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","volume":"30","author":"Heusel"},{"key":"ref55","article-title":"Demystifying MMD GANs","volume-title":"Proc. 6th Int. Conf. Learn. Represent","author":"Binkowski"},{"key":"ref56","article-title":"CompressAI: A PyTorch library and evaluation platform for end-to-end compression research","author":"B\u00e9gaint","year":"2020","journal-title":"arXiv:2011.03029"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180208"},{"key":"ref58","article-title":"Understanding the vulnerability of clip to image compression","volume-title":"Proc. Workshop NeurIPS","author":"Chen"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11658813.pdf?arnumber=11658813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T05:35:06Z","timestamp":1787636106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11658813\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3723242","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}