{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:57:42Z","timestamp":1773154662347,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100009427","name":"Telecommunications Advancement Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009427","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,8]]},"DOI":"10.1109\/vcip63160.2024.10849863","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:36:57Z","timestamp":1738003017000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["LMM-driven Semantic Image-Text Coding for Ultra Low-bitrate Learned Image Compression"],"prefix":"10.1109","author":[{"given":"Shimon","family":"Murai","sequence":"first","affiliation":[{"name":"Waseda University,School of Fundamental Science and Engineering,Tokyo,Japan"}]},{"given":"Heming","family":"Sun","sequence":"additional","affiliation":[{"name":"Yokohama National University,Faculty of Engineering,Japan"}]},{"given":"Jiro","family":"Katto","sequence":"additional","affiliation":[{"name":"Waseda University,School of Fundamental Science and Engineering,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2024.3515874"},{"key":"ref4","article-title":"Text + sketch: Image compression at ultra low rates","volume-title":"ICML 2023 Workshop Neural Compression: From Information Theory to Applications","author":"Lei"},{"key":"ref5","article-title":"Towards image compression with perfect realism at ultra-low bitrates","volume-title":"The Twelfth International Conference on Learning Representations","author":"Careil"},{"key":"ref6","article-title":"LLMZip: Lossless Text Compression using Large Language Models","author":"Valmeekam","year":"2023"},{"key":"ref7","article-title":"Language modeling is compression","volume-title":"The Twelfth International Conference on Learning Representations","author":"Deletang"},{"key":"ref8","article-title":"Kodak lossless true color image suite"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2024.3403524"},{"key":"ref10","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Heusel","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref12","first-page":"11913","article-title":"High-Fidelity Generative Image Compression","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Mentzer","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00187"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412185"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02138"},{"key":"ref16","author":"Hoogeboom","year":"2023","journal-title":"High-Fidelity Image Compression with Score-based Generative Models."},{"key":"ref17","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"ref20","article-title":"Visual instruction tuning","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Liu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_23"},{"key":"ref22","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref23","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref26","article-title":"3rd workshop and challenge on learned image compression"},{"key":"ref27","article-title":"Calculation of average psnr differences between rdcurves","author":"Bj\u00f8ntegaard","year":"2001"}],"event":{"name":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","location":"Tokyo, Japan","start":{"date-parts":[[2024,12,8]]},"end":{"date-parts":[[2024,12,11]]}},"container-title":["2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10849624\/10849781\/10849863.pdf?arnumber=10849863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:10:55Z","timestamp":1738044655000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/vcip63160.2024.10849863","relation":{},"subject":[],"published":{"date-parts":[[2024,12,8]]}}}