{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T06:57:38Z","timestamp":1781852258242,"version":"3.54.5"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62001272"],"award-info":[{"award-number":["62001272"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Shandong Province, China","award":["ZR2023MF015"],"award-info":[{"award-number":["ZR2023MF015"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3379885","type":"journal-article","created":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T18:24:30Z","timestamp":1710959070000},"page":"47246-47257","source":"Crossref","is-referenced-by-count":11,"title":["Temporal Shift Module-Based Vision Transformer Network for Action Recognition"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2447-8786","authenticated-orcid":false,"given":"Kunpeng","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Shandong University of Technology, Zibo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9466-9456","authenticated-orcid":false,"given":"Mengyan","family":"Lyu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Shandong University of Technology, Zibo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9175-9771","authenticated-orcid":false,"given":"Xinxin","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Shandong University of Technology, Zibo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4300-1789","authenticated-orcid":false,"given":"Liye","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Shandong University of Technology, Zibo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5999-2126","authenticated-orcid":false,"given":"Cong","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Shandong University of Technology, Zibo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1606.04797"},{"issue":"1","key":"ref12","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Simonyan"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref14","article-title":"Towards good practices for very deep two-stream ConvNets","author":"Wang","year":"2015","journal-title":"arXiv:1507.02159"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475272"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref30","article-title":"An image is worth 16\u271716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_23"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref35","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref38","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"arXiv:2203.12602"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547908"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00100"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CAC51589.2020.9326923"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3268134"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-021-0236-9"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/app12125784"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/iccece58074.2023.10135328"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3235522"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/icce56470.2023.10043568"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/iccea58433.2023.10135414"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747276"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/mlccim60412.2023.00027"},{"key":"ref52","article-title":"Video action recognition collaborative learning with dynamics via PSO-ConvNet transformer","author":"Phong","year":"2023","journal-title":"arXiv:2302.09187"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01804"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10476575.pdf?arnumber=10476575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:43:58Z","timestamp":1712691838000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10476575\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3379885","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}