{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:07:53Z","timestamp":1761898073837,"version":"3.33.0"},"reference-count":55,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,8]]},"DOI":"10.1109\/vcip63160.2024.10849922","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":1,"title":["Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMs"],"prefix":"10.1109","author":[{"given":"Jinming","family":"Liu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Yuntao","family":"Wei","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"}]},{"given":"Junyan","family":"Lin","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"}]},{"given":"Shengyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"}]},{"given":"Heming","family":"Sun","sequence":"additional","affiliation":[{"name":"Yokohama National University"}]},{"given":"Zhibo","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"}]},{"given":"Xin","family":"Jin","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/30.125072"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref3","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"journal-title":"Vvc official test model vtm","year":"2021","author":"Team","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02138"},{"article-title":"Towards image compression with perfect realism at ultra-low bitrates","volume-title":"The Twelfth International Conference on Learning Representations","author":"Careil","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016485"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/DCC50243.2021.00024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01581"},{"article-title":"Scaling laws for neural language models","year":"2020","author":"Kaplan","key":"ref13"},{"key":"ref14","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"article-title":"Emergent abilities of large language models","year":"2022","author":"Wei","key":"ref15"},{"key":"ref16","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref17"},{"article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","year":"2024","author":"Ren","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2020.3042517","article-title":"Semantic structured image coding framework for multiple intelligent applications","volume-title":"TCSVT","author":"Sun"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058584"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"article-title":"End-to-end optimized image compression","volume-title":"ICLR","author":"Ball\u00e9","key":"ref25"},{"article-title":"Variational image compression with a scale hyperprior","volume-title":"ICLR","author":"Ball\u00e9","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/PCS48520.2019.8954525"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103816"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/PCS56426.2022.10018036"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP59821.2023.10402659"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP53242.2021.9675369"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"issue":"1","key":"ref41","first-page":"1","article-title":"The dawn of lmms: Preliminary explorations with gpt-4v(ision)","volume":"9","author":"Yang","year":"2023"},{"article-title":"Ferret: Refer and ground anything anywhere at any granularity","year":"2023","author":"You","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"article-title":"Textmonkey: An ocr-free large multimodal model for understanding document","year":"2024","author":"Liu","key":"ref44"},{"article-title":"Recognize anything: A strong image tagging model","year":"2023","author":"Zhang","key":"ref45"},{"article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","year":"2023","author":"Chen","key":"ref46"},{"key":"ref47","first-page":"19 730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref48","first-page":"arXiv","article-title":"An empirical study of scaling law for ocr","author":"Rang","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612041"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"article-title":"The caltech-ucsd birds-200-2011 dataset","year":"2011","author":"Wah","key":"ref53"},{"article-title":"Calculation of average psnr differences between rd-curves","year":"2001","author":"Bj\u00f8ntegaard","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"}],"event":{"name":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","start":{"date-parts":[[2024,12,8]]},"location":"Tokyo, Japan","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\/10849922.pdf?arnumber=10849922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:08:51Z","timestamp":1738044531000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849922\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/vcip63160.2024.10849922","relation":{},"subject":[],"published":{"date-parts":[[2024,12,8]]}}}