{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T18:36:22Z","timestamp":1783362982378,"version":"3.54.6"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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":["62301310"],"award-info":[{"award-number":["62301310"]}],"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":["62225112"],"award-info":[{"award-number":["62225112"]}],"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":["623B2073"],"award-info":[{"award-number":["623B2073"]}],"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":["62471290"],"award-info":[{"award-number":["62471290"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019065","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2024NSFSC1426"],"award-info":[{"award-number":["2024NSFSC1426"]}],"id":[{"id":"10.13039\/501100019065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2024.3515874","type":"journal-article","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T19:39:07Z","timestamp":1735328347000},"page":"335-349","source":"Crossref","is-referenced-by-count":19,"title":["MISC: Ultra-Low Bitrate Image Semantic Compression Driven by Large Multimodal Model"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0634-1710","authenticated-orcid":false,"given":"Chunyi","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-0090","authenticated-orcid":false,"given":"Guo","family":"Lu","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8984-0425","authenticated-orcid":false,"given":"Donghui","family":"Feng","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8642-8101","authenticated-orcid":false,"given":"Haoning","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7247-7938","authenticated-orcid":false,"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6377-4730","authenticated-orcid":false,"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[{"name":"John Hopcroft Center, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, 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":"Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8799-1182","authenticated-orcid":false,"given":"Wenjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3343912"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3319275"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3065244"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB55706.2022.9828771"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2023.3345656"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00652"},{"key":"ref7","first-page":"675","article-title":"Rethinking lossy compression: The rate-distortion-perception tradeoff","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blau"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647820"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/dcc58796.2024.00028"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01809-7"},{"key":"ref11","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref12","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref14","article-title":"Text-guided synthesis of artistic images with retrieval-augmented diffusion models","author":"Rombach","year":"2022","journal-title":"arXiv:2207.13038"},{"key":"ref15","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref16","article-title":"AI-generated content (AIGC): A survey","author":"Wu","year":"2023","journal-title":"arXiv:2304.06632"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/79.952804"},{"key":"ref18","first-page":"2922","article-title":"Real-time adaptive image compression","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Rippel"},{"key":"ref19","first-page":"10794","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Minnen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3323015"},{"key":"ref21","article-title":"Lossless image compression through super-resolution","author":"Cao","year":"2020","journal-title":"arXiv:2004.02872"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00085"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3317424"},{"key":"ref25","first-page":"11913","article-title":"High-fidelity generative image compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mentzer"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02138"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00288"},{"key":"ref28","article-title":"Lossy image compression with conditional diffusion models","author":"Yang","year":"2022","journal-title":"arXiv:2209.06950"},{"key":"ref29","article-title":"Extreme generative image compression by learning text embedding from diffusion models","author":"Pan","year":"2022","journal-title":"arXiv:2211.07793"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475558"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3364153"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP59012.2023.10337734"},{"key":"ref33","article-title":"High-fidelity image compression with score-based generative models","author":"Hoogeboom","year":"2023","journal-title":"arXiv:2305.18231"},{"key":"ref34","article-title":"Text + sketch: Image compression at ultra low rates","author":"Lei","year":"2023","journal-title":"arXiv:2307.01944"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref38","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":"ref39","first-page":"25426","article-title":"Improving statistical fidelity for neural image compression with implicit local likelihood models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Muckley"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"ref41","article-title":"Towards image compression with perfect realism at ultra-low bitrates","author":"Careil","year":"2023","journal-title":"arXiv:2310.10325"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02465"},{"key":"ref43","volume-title":"Calculation Average Psnr Differences Between RD-curves","author":"Bjontegaard","year":"2001"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3034501"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00082"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref49","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":"ref50","article-title":"Q-bench: A benchmark for general-purpose foundation models on low-level vision","author":"Wu","year":"2023","journal-title":"arXiv:2309.14181"},{"key":"ref51","article-title":"Q-instruct: Improving low-level visual abilities for multi-modality foundation models","author":"Wu","year":"2023","journal-title":"arXiv:2311.06783"},{"key":"ref52","article-title":"Q-boost: On visual quality assessment ability of low-level multi-modality foundation models","author":"Zhang","year":"2023","journal-title":"arXiv:2312.15300"},{"key":"ref53","article-title":"Q-align: Teaching LMMs for visual scoring via discrete text-defined levels","author":"Wu","year":"2023","journal-title":"arXiv:2312.17090"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687390"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3643817"},{"key":"ref56","article-title":"Advancing zero-shot digital human quality assessment through text-prompted evaluation","author":"Zhang","year":"2023","journal-title":"arXiv:2307.02808"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00286"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00081"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949270"},{"key":"ref60","article-title":"A closer look at the explainability of contrastive language-image pre-training","author":"Li","year":"2023","journal-title":"arXiv:2304.05653"},{"key":"ref61","article-title":"DiffBIR: Towards blind image restoration with generative diffusion prior","author":"Lin","year":"2023","journal-title":"arXiv:2308.15070"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref66","article-title":"Adversarial diffusion distillation","author":"Sauer","year":"2023","journal-title":"arXiv:2311.17042"},{"key":"ref67","volume-title":"Midjourney","author":"Holz","year":"2023"},{"key":"ref68","article-title":"Progressive knowledge distillation of stable diffusion XL using layer level loss","author":"Gupta","year":"2024","journal-title":"arXiv:2401.02677"},{"key":"ref69","volume-title":"Playground-v2-1024Px-Aesthetic","year":"2023"},{"key":"ref70","volume-title":"Dreamlike-Photoreal-2.0","year":"2023"},{"key":"ref71","article-title":"PixArt-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv:2310.00426"},{"key":"ref72","volume-title":"If-I-Xl-V1.0","year":"2023"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.2312\/stag.20141242"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref76","first-page":"4961","article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ball\u00e9"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref80","article-title":"DiffusionDB: A large-scale prompt gallery dataset for text-to-image generative models","author":"Wang","year":"2022","journal-title":"arXiv:2210.14896"},{"key":"ref81","article-title":"GenImage: A million-scale benchmark for detecting AI-generated image","author":"Zhu","year":"2023","journal-title":"arXiv:2306.08571"},{"key":"ref82","volume-title":"Pokemon Blip Captions","author":"Pinkney","year":"2022"},{"key":"ref83","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10816592.pdf?arnumber=10816592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:28:04Z","timestamp":1736972884000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10816592\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3515874","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}