{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:13Z","timestamp":1761894673881,"version":"build-2065373602"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209953","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Vote & Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer"],"prefix":"10.1109","author":[{"given":"Shuai","family":"Peng","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Fu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baole","family":"Wei","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangcai","family":"Gao","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Tang","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref4","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00085"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"ref9","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"},{"article-title":"What do self-supervised vision transformers learn?","volume-title":"The Eleventh International Conference on Learning Representations","author":"Park","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"Kay","key":"ref12"},{"key":"ref13","first-page":"5842","article-title":"The","volume-title":"something something\" video database for learning and evaluating visual common sense,\" in Proceedings of the IEEE international conference on computer vision","author":"Goyal"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_26"},{"article-title":"Learning to merge tokens in vision transformers","year":"2022","author":"Renggli","key":"ref17"},{"article-title":"Token merging: Your vit but faster","volume-title":"The Eleventh International Conference on Learning Representations","author":"Bolya","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00141"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00088"},{"key":"ref21","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"ref23","first-page":"24898","article-title":"Ia-red \u02c62: Interpretability-aware redundancy reduction for vision transformers","volume":"34","author":"Pan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01199"},{"article-title":"Evit: Expediting vision transformers via token reorganizations","volume-title":"International Conference on Learning Representations","author":"Liang","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00996"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01521"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01554"},{"key":"ref30","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume":"34","author":"Patrick","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209953.pdf?arnumber=11209953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:08Z","timestamp":1761888788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209953\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209953","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}