{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:28:46Z","timestamp":1778693326983,"version":"3.51.4"},"reference-count":93,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01612","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"01-12","source":"Crossref","is-referenced-by-count":2,"title":["GIViC: Generative Implicit Video Compression"],"prefix":"10.1109","author":[{"given":"Ge","family":"Gao","sequence":"first","affiliation":[{"name":"University of Bristol,Visual Information Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyue","family":"Teng","sequence":"additional","affiliation":[{"name":"University of Bristol,Visual Information Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianhao","family":"Peng","sequence":"additional","affiliation":[{"name":"University of Bristol,Visual Information Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Bristol,Visual Information Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Bull","sequence":"additional","affiliation":[{"name":"University of Bristol,Visual Information Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2878952"},{"key":"ref2","first-page":"12367","article-title":"Universally quantized neural compression","volume":"33","author":"Agustsson","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222144"},{"key":"ref4","first-page":"3","article-title":"Variational image compression with a scale hyperprior","volume-title":"International Conference on Learning Representations","author":"Ball\u00e9","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1789"},{"key":"ref6","first-page":"6","article-title":"Calculation of average PSNR differences between rd-curves","author":"Bjontegaard","year":"2001","journal-title":"ITU SG16 Doc. VCEG-M33"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref8","first-page":"JVET-J1010","article-title":"JVET-J1010: JVET common test conditions and software reference configurations","volume-title":"10th Meeting of the Joint Video Experts Team","author":"Boyce","year":"2018"},{"key":"ref9","first-page":"JVET-J1010","article-title":"JVET-J1010: JVET common test conditions and software reference configurations","volume-title":"10th Meeting of the Joint Video Experts Team","author":"Boyce","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref11","first-page":"6","article-title":"Algorithm description for Versatile Video Coding and Test Model 19 (VTM 19)","volume-title":"the JVET meeting. ITU-T and ISO\/IEC","volume":"2","author":"Browne","year":"2023"},{"key":"ref12","volume-title":"Intelligent Image and Video Compression: Communicating Pictures","author":"Bull","year":"2021"},{"key":"ref13","first-page":"21557","article-title":"NeRV: Neural representations for videos","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00990"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27912"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref18","first-page":"3","article-title":"Soft diffusion: Score matching with general corruptions","author":"Daras","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref19","first-page":"2","article-title":"Language modeling is compression","volume-title":"International Conference on Learning Representations","author":"Deletang","year":"2024"},{"key":"ref20","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00028"},{"key":"ref22","first-page":"2","article-title":"COIN: Compression with implicit neural representations","volume-title":"International Conference on Learning Representations Workshop on Neural Compression: From Information Theory to Applications","author":"Dupont","year":"2021"},{"key":"ref23","first-page":"4","article-title":"Image compression with product quantized masked image modeling","author":"El-Nouby","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32315"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01774"},{"key":"ref26","first-page":"3","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"5","volume":"2","author":"Gu","year":"2023","journal-title":"Mamba: Linear-time sequence modeling with selective state spaces"},{"key":"ref28","first-page":"3","article-title":"f-DM: A multi-stage diffusion model via progressive signal transformation","volume-title":"International Conference on Learning Representations","author":"Gu","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058584"},{"key":"ref30","first-page":"2","author":"Han","year":"2015","journal-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00594"},{"key":"ref32","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"47","key":"ref33","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_12"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01380"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"ref37","first-page":"2","author":"Huang","year":"2024","journal-title":"Compression represents intelligence linearly"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00687"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00219"},{"key":"ref40","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"International Conference on Machine Learning","author":"Katharopoulos","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00893"},{"key":"ref42","first-page":"3","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref43","first-page":"6","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0022-1694(80)90036-0"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3177"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4210"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612444"},{"key":"ref48","first-page":"18114","article-title":"Deep contextual video compression","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02466"},{"key":"ref51","first-page":"6","article-title":"Toward A Practical Perceptual Video Quality Metric","author":"Li","year":"2016","journal-title":"Netflix TechBlog"},{"key":"ref52","first-page":"8","author":"Liu","year":"2022","journal-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0951"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0908-6_17"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.936"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/PCS60826.2024.10566283"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72848-8_18"},{"key":"ref60","first-page":"2","author":"Qin","year":"2024","journal-title":"Mambavc: Learned visual compression with selective state spaces"},{"key":"ref61","first-page":"5","article-title":"HGRN2: Gated linear RNNs with state expansion","volume-title":"First Conference on Language Modeling","author":"Qin","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_17"},{"key":"ref63","article-title":"Generative modelling with inverse heat dissipation","volume-title":"International Conference on Learning Representations","author":"Rissanen","year":"2023"},{"key":"ref64","first-page":"6","article-title":"High efficiency video coding (HEVC) test model 16 (HM 16) improved encoder description update 16","volume-title":"the JVET meeting. ITU-T and ISO\/IEC","author":"Rosewarne","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.09661"},{"key":"ref66","first-page":"3","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","volume":"2","author":"Song","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref68","first-page":"2","volume-title":"ECM: Enhanced compression model","author":"Suehring","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref70","first-page":"2","author":"Sun","year":"2024","journal-title":"Autoregressive model beats diffusion: Llama for scalable image generation"},{"key":"ref71","first-page":"8","volume-title":"Relay diffusion: Unifying diffusion process across resolutions for image synthesis","volume":"3","author":"Teng","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP63160.2024.10849793"},{"key":"ref73","first-page":"3","author":"Theis","year":"2022","journal-title":"Lossy compression with gaussian diffusion"},{"key":"ref74","first-page":"2","article-title":"Overfitting for fun and profit: Instance-adaptive data compression","volume-title":"International Conference on Learning Representations","author":"van Rozendaal","year":"2021"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"ref77","first-page":"2","author":"Wang","year":"2024","journal-title":"Emu3: Next-token prediction is all you need"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref80","first-page":"2","article-title":"MIMT: Masked image modeling transformer for video compression","volume-title":"International Conference on Learning Representations","volume":"1","author":"Xiang","year":"2022"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0975"},{"key":"ref82","first-page":"38377","article-title":"Bit allocation using optimization","volume-title":"International Conference on Learning Representations","author":"Xu","year":"2023"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02172"},{"key":"ref85","first-page":"3","article-title":"Lossy image compression with conditional diffusion models","volume":"36","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref86","first-page":"5","volume":"2","author":"Yang","year":"2023","journal-title":"Gated linear attention transformers with hardware-efficient training"},{"key":"ref87","first-page":"3","article-title":"Efficient video diffusion models via content-frame motion-latent decomposition","volume-title":"International Conference on Learning Representations","author":"Yu","year":"2024"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2021.3052437"},{"key":"ref89","first-page":"3","author":"Zhang","year":"2024","journal-title":"When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00247"},{"key":"ref92","first-page":"2","article-title":"Neural rate control for learned video compression","volume-title":"International Conference on Learning Representations","author":"Zhang","year":"2024"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33165"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444235.pdf?arnumber=11444235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:12Z","timestamp":1777529832000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":93,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01612","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}