{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:38:43Z","timestamp":1781714323117,"version":"3.54.5"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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","award":["62376052"],"award-info":[{"award-number":["62376052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tnnls.2025.3550910","type":"journal-article","created":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T14:04:23Z","timestamp":1744380263000},"page":"15449-15462","source":"Crossref","is-referenced-by-count":3,"title":["End-to-End Streaming Video Temporal Action Segmentation With Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0777-5499","authenticated-orcid":false,"given":"Jin-Rong","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4157-8151","authenticated-orcid":false,"given":"Wu-Jun","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3823-4200","authenticated-orcid":false,"given":"Sheng-Lan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Innovation and Entrepreneurship, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2298-0540","authenticated-orcid":false,"given":"Yun-Heng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi-Feng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4942-2293","authenticated-orcid":false,"given":"Lin","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Innovation and Entrepreneurship, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Temporal action segmentation: An analysis of modern techniques","author":"Ding","year":"2022","journal-title":"arXiv:2210.10352"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.49"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3201208"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01722"},{"key":"ref6","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhan"},{"key":"ref7","first-page":"1","article-title":"Dual-mode ASR: Unify and improve streaming ASR with full-context modeling","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/sym11081018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-27529-7_29"},{"key":"ref10","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Graves"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.121"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01599"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5_2"},{"key":"ref14","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00705"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021756"},{"key":"ref19","article-title":"Coarse to fine multi-resolution temporal convolutional network","author":"Singhania","year":"2021","journal-title":"arXiv:2105.10859"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859819"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285416"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00237"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2923712"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01341"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01954"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1090\/s0002-9904-1954-09848-8"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12255"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3072412"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/app122010339"},{"key":"ref33","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref35","first-page":"33248","article-title":"Block-recurrent transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Hutchins"},{"key":"ref36","article-title":"RoFormer: Enhanced transformer with rotary position embedding","author":"Su","year":"2021","journal-title":"arXiv:2104.09864"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01926"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01653"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01404"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_4"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00930"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.341"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-12939-2_20"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref53","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref55","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv:2110.02178"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3165153"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00113"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11114436\/10963907.pdf?arnumber=10963907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:00:55Z","timestamp":1754503255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10963907\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":61,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3550910","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}