{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:03:02Z","timestamp":1766138582590,"version":"3.44.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"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":["62025101","62088102","62371008","62101007"],"award-info":[{"award-number":["62025101","62088102","62371008","62101007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Xplore Prize"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tcsvt.2024.3364153","type":"journal-article","created":{"date-parts":[[2024,2,8]],"date-time":"2024-02-08T13:59:48Z","timestamp":1707400788000},"page":"6978-6992","source":"Crossref","is-referenced-by-count":4,"title":["Rate-Distortion Optimized Cross Modal Compression With Multiple Domains"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8734-1021","authenticated-orcid":false,"given":"Junlong","family":"Gao","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7418-6245","authenticated-orcid":false,"given":"Chuanmin","family":"Jia","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8026-9349","authenticated-orcid":false,"given":"Zhimeng","family":"Huang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7665-7434","authenticated-orcid":false,"given":"Shanshe","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2731-5403","authenticated-orcid":false,"given":"Siwei","family":"Ma","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8070-802X","authenticated-orcid":false,"given":"Wen","family":"Gao","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1117\/12.19537"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475558"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2001239"},{"key":"ref6","article-title":"Large language models are human-level prompt engineers","author":"Zhou","year":"2022","journal-title":"arXiv:2211.01910"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310657"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DCC55655.2023.00030"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262514620.001.0001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2000.838192"},{"volume-title":"BPG Image Format","year":"2015","author":"Bellard","key":"ref12"},{"key":"ref13","first-page":"10794","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Minnen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016485"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"article-title":"Sequence level training with recurrent neural networks","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Ranzato","key":"ref16"},{"key":"ref17","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00646"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1952.273898"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.622"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018650"},{"key":"ref31","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref35","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref36","first-page":"6629","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":"ref37","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ball\u00e9","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"article-title":"The caltech-UCSD birds-200\u20132011 dataset","year":"2011","author":"Wah","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0612-7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10430161.pdf?arnumber=10430161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:48:25Z","timestamp":1755546505000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10430161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":43,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3364153","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}