{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:10:27Z","timestamp":1777889427457,"version":"3.51.4"},"reference-count":54,"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\/iccv51701.2025.01974","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21254-21264","source":"Crossref","is-referenced-by-count":0,"title":["Principles of Visual Tokens for Efficient Video Understanding"],"prefix":"10.1109","author":[{"given":"Xinyue","family":"Hao","sequence":"first","affiliation":[{"name":"University of Edinburgh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gen","family":"Li","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shreyank N","family":"Gowda","sequence":"additional","affiliation":[{"name":"University of Nottingham"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert B.","family":"Fisher","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Huang","sequence":"additional","affiliation":[{"name":"Scaled Foundations"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anurag","family":"Arnab","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura","family":"Sevilla-Lara","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref2","author":"Bertasius","year":"2021","journal-title":"Is space-time attention all you need for video understanding? In ICML, page 4"},{"key":"ref3","article-title":"Token merging: Your ViT but faster","volume-title":"International Conference on Learning Representations","author":"Bolya","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref5","article-title":"Space-time mixing attention for video transformer","author":"Bulat","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01776"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01554"},{"key":"ref11","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3633781"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92089-9_24"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_26"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01576"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_19"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00264"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1919"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_10"},{"key":"ref31","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","author":"Patrick","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2022.3148714"},{"key":"ref33","author":"Peters","year":"2024","journal-title":"How does the primate brain combine generative and discriminative computations in vision? CoRR, abs\/2401"},{"key":"ref34","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref35","author":"Ryoo","year":"2021","journal-title":"Tokenlearner: What can 8 learned tokens do for images and videos? arXiv preprint arXiv:2106"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00058"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref40","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron","year":"2021"},{"key":"ref41","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331841"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_11"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01267"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00631"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"ref49","article-title":"Aim: Adapting image models for efficient video action recognition","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yang","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref51","article-title":"Self-chained image-language model for video localization and question answering","author":"Yu","year":"2024","journal-title":"NeurIPS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00320"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00233"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"}],"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\/11445158.pdf?arnumber=11445158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:13:03Z","timestamp":1777612383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01974","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}