{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T19:46:10Z","timestamp":1793130370664,"version":"4.5.0"},"reference-count":109,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"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":"crossref","award":["62021001"],"award-info":[{"award-number":["62021001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tpami.2026.3689998","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:35:44Z","timestamp":1777923344000},"page":"10535-10550","source":"Crossref","is-referenced-by-count":2,"title":["NVC-1B: Scaling up Neural Video Coding Models"],"prefix":"10.1109","volume":"48","author":[{"given":"Chuanbo","family":"Tang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7350-4929","authenticated-orcid":false,"given":"Xihua","family":"Sheng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7163-6263","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9100-2906","authenticated-orcid":false,"given":"Dong","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7266-5579","authenticated-orcid":false,"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00713"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_15"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_27"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0951"},{"key":"ref8","first-page":"21557","article-title":"NeRV: Neural representations for videos","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00990"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00202"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3177"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4210"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6825"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01421"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2988453"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00360"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00853"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01031"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00355"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00652"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3043590"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00076"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3035680"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3138300"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2892608"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233221"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3287495"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3277343"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3222418"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3220421"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/DCC55655.2023.00028"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3360248"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356548"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547845"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_12"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3276333"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126396"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3395025"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28317"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01171"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00687"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01170"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00201"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02466"},{"key":"ref47","article-title":"Scaling learned image compression models up to 1 billion","author":"Li","year":"2025"},{"key":"ref48","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref49","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref50","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref51","article-title":"Deepseek-V3 technical report","author":"Liu","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref54","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref55","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dehghani"},{"key":"ref56","article-title":"FLUX. 1 Kontext: Flow matching for in-context image generation and editing in latent space","author":"Batifol","year":"2025"},{"key":"ref57","article-title":"Qwen-image technical report","author":"Wu","year":"2025"},{"key":"ref58","article-title":"WAN: Open and advanced large-scale video generative models","author":"Wan","year":"2025"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref60","article-title":"VTM-13.2","year":"2022"},{"key":"ref61","first-page":"87","article-title":"AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration","volume-title":"Proc. Mach. Learn. Syst.","volume":"6","author":"Lin"},{"key":"ref62","article-title":"The era of 1-bit LLMs: All large language models are in 1.58 bits","author":"Ma","year":"2024"},{"key":"ref63","article-title":"Challenges and applications of large language models","author":"Kaddour","year":"2023"},{"key":"ref64","article-title":"MiniLLM: Knowledge distillation of large language models","author":"Gu","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29908"},{"key":"ref66","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref67","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref68","article-title":"OpenELM: An efficient language model family with open training and inference framework","author":"Mehta","year":"2024"},{"key":"ref69","article-title":"On-device language models: A comprehensive review","author":"Xu","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_26"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"ref72","first-page":"18114","article-title":"Deep contextual video compression","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00583"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3150014"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_36"},{"key":"ref76","article-title":"MIMT: Masked image modeling transformer for video compression","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Xiang"},{"key":"ref77","first-page":"38377","article-title":"Bit allocation using optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3427426"},{"key":"ref79","article-title":"C3: High-performance and low-complexity neural compression from a single image or video","author":"Kim","year":"2023"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28733"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2024.3387301"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00687"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref84","first-page":"5547","article-title":"GLaM: Efficient scaling of language models with mixture-of-experts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du"},{"issue":"240","key":"ref85","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref86","article-title":"PaLM 2 technical report","author":"Anil","year":"2023"},{"key":"ref87","article-title":"LlaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref88","article-title":"Introducing meta LLaMA 3: The most capable openly available LLM to date","author":"Meta","year":"2024","journal-title":"Meta AI."},{"key":"ref89","article-title":"Introducing mistral 7B","year":"2023"},{"key":"ref90","article-title":"PaLI: A jointly-scaled multilingual language-image model","author":"Chen","year":"2022"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref92","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"ref94","article-title":"End-to-end optimized image compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ball\u00e9"},{"key":"ref95","article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Ball\u00e9","year":"2018"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3316429"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611960"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00592"},{"key":"ref100","article-title":"Common HM test conditions and software reference configurations (JCTVC-L1100)","author":"Bossen","year":"2013","journal-title":"Joint Collaborative Team Video Coding ITU-T SG"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3608643"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"ref104","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref105","article-title":"ECM-13.0","year":"2024"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221192"},{"key":"ref107","article-title":"Calculation of average PSNR differences between RD-curves","author":"Bjontegaard","year":"2001","journal-title":"VCEG-M33"},{"key":"ref108","first-page":"2022","article-title":"Transformer-based transform coding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11643729\/11505036.pdf?arnumber=11505036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:07:19Z","timestamp":1786388839000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11505036\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":109,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3689998","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}