{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:27:44Z","timestamp":1761895664893,"version":"build-2065373602"},"reference-count":22,"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007219","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\/icme59968.2025.11209327","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":["ESTJ: Efficient Semantic Segmentation via Token Joint Merging"],"prefix":"10.1109","author":[{"given":"Ziniu","family":"Liu","sequence":"first","affiliation":[{"name":"Tongji University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Information and Communication Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengxia","family":"Han","sequence":"additional","affiliation":[{"name":"Tongji University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingtong","family":"Liu","sequence":"additional","affiliation":[{"name":"Tongji University,Guohao College,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuan","family":"Liu","sequence":"additional","affiliation":[{"name":"China Electric Power Research Institute,Department of Information and Communication,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Zhang","sequence":"additional","affiliation":[{"name":"China Electric Power Research Institute,Department of Information and Communication,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Deng","sequence":"additional","affiliation":[{"name":"Tongji University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjie","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tongji University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"ICLR","author":"Dosovitskiy","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","key":"ref1"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICCV48922.2021.00717"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref4","article-title":"Segvit: Semantic segmentation with plain vision transformers","volume":"35","author":"Zhang","year":"2022","journal-title":"NeurIPS"},{"key":"ref5","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","author":"Rao","year":"2021","journal-title":"NeurIPS"},{"volume-title":"ICLR","author":"Liang","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/WACV57701.2024.00184"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICCV51070.2023.00078"},{"volume-title":"ICLR","author":"Bolya","article-title":"Token merging: Your vit but faster","key":"ref10"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CVPR52729.2023.02263"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/CVPR52733.2024.01493"},{"year":"2024","author":"Tran","article-title":"Accelerating transformers with spectrum-preserving token merging","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/CVPR.2017.544"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/CVPR52688.2022.01054"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICCV51070.2023.01574"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/WACV57701.2024.00141"},{"key":"ref18","article-title":"Ailurus: a scalable vit framework for dense prediction","volume":"36","author":"Li","year":"2024","journal-title":"NeurIPS"},{"year":"2016","author":"Ba","article-title":"Layer normalization","key":"ref19"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPR.2016.350"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR.2014.119"}],"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\/11209327.pdf?arnumber=11209327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:56:13Z","timestamp":1761890173000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209327","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}