{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:20:44Z","timestamp":1777890044592,"version":"3.51.4"},"reference-count":46,"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\/iccv51701.2025.01755","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18885-18894","source":"Crossref","is-referenced-by-count":0,"title":["Context Guided Transformer Entropy Modeling for Video Compression"],"prefix":"10.1109","author":[{"given":"Junlong","family":"Tong","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Digital Twin, EIT,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaohui","family":"Jin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyu","family":"Shen","sequence":"additional","affiliation":[{"name":"Institute of Digital Twin, EIT,Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00853"},{"key":"ref2","article-title":"Variational image compression with a scale hyperprior","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ball\u00e9"},{"key":"ref3","article-title":"Beit: Bert pre-training of image transformers","volume-title":"International Conference on Learning Representations","author":"Bao"},{"key":"ref4","article-title":"Calculation of average psnr differences between rd-curves","author":"Bjontegaard","year":"2001","journal-title":"ITU SG16 Doc. VCEG-M33"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611960"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00652"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01774"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3316429"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00713"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_12"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00583"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3371686"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4210"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103090"},{"key":"ref19","first-page":"18114","article-title":"Deep contextual video compression","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547845"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02466"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_27"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3227717"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0951"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00492"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190935"},{"key":"ref33","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume":"31","author":"Minnen","year":"2018","journal-title":"Advances in neural information processing systems (NeurIPS)"},{"key":"ref34","first-page":"17656","article-title":"Differentiable top-k classification learning","volume-title":"International Conference on Machine Learning","author":"Petersen"},{"key":"ref35","article-title":"Entroformer: A transformer-based entropy model for learned image compression","volume-title":"International Conference on Learning Representations (ICLR)","author":"Qian"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3243465"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3220421"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01147"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"ref42","article-title":"Mimt: Masked image modeling transformer for video compression","volume-title":"International Conference on Learning Representations(ICLR)","author":"Xiang"},{"key":"ref43","first-page":"20520","article-title":"Differentiable top-k with optimal transport","volume":"33","author":"Xie","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00666"},{"key":"ref46","article-title":"Transformerbased transform coding","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhu"}],"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\/11446313.pdf?arnumber=11446313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:25:42Z","timestamp":1777613142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446313\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01755","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}