{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:05:50Z","timestamp":1761897950950,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,17]],"date-time":"2023-11-17T00:00:00Z","timestamp":1700179200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,17]],"date-time":"2023-11-17T00:00:00Z","timestamp":1700179200000},"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":[[2023,11,17]]},"DOI":"10.1109\/iske60036.2023.10481438","type":"proceedings-article","created":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T20:33:29Z","timestamp":1712608409000},"page":"316-323","source":"Crossref","is-referenced-by-count":3,"title":["Streaming Video Temporal Action Segmentation in Real Time"],"prefix":"10.1109","author":[{"given":"Wujun","family":"Wen","sequence":"first","affiliation":[{"name":"Dalian University of Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunheng","family":"Li","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuben","family":"Dong","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Feng","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanxiao","family":"Yang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenlan","family":"Liu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01926"},{"journal-title":"Asformer: Transformer for action segmentation","year":"2021","author":"Yi","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01599"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"ref7","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01576"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.03.069"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.121"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01320"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00356"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01404"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00474"},{"journal-title":"Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer","year":"2021","author":"Mehta","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3165153"}],"event":{"name":"2023 18th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","start":{"date-parts":[[2023,11,17]]},"location":"Fuzhou, China","end":{"date-parts":[[2023,11,19]]}},"container-title":["2023 18th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10480909\/10480924\/10481438.pdf?arnumber=10481438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T05:10:45Z","timestamp":1712639445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10481438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,17]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/iske60036.2023.10481438","relation":{},"subject":[],"published":{"date-parts":[[2023,11,17]]}}}