{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T04:46:36Z","timestamp":1776401196669,"version":"3.51.2"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"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":["U21A20455"],"award-info":[{"award-number":["U21A20455"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972265"],"award-info":[{"award-number":["61972265"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11871348"],"award-info":[{"award-number":["11871348"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872429"],"award-info":[{"award-number":["61872429"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province of China","doi-asserted-by":"publisher","award":["2020B1515310008"],"award-info":[{"award-number":["2020B1515310008"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Educational Commission of Guangdong Province of China","award":["2019KZDZX1007"],"award-info":[{"award-number":["2019KZDZX1007"]}]},{"DOI":"10.13039\/100000893","name":"Simons Foundation","doi-asserted-by":"publisher","award":["353185"],"award-info":[{"award-number":["353185"]}],"id":[{"id":"10.13039\/100000893","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF2110218"],"award-info":[{"award-number":["W911NF2110218"]}],"id":[{"id":"10.13039\/100000183","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":[[2024,2]]},"DOI":"10.1109\/tnnls.2022.3190367","type":"journal-article","created":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T19:31:58Z","timestamp":1658345518000},"page":"2496-2509","source":"Crossref","is-referenced-by-count":40,"title":["An Effective Video Transformer With Synchronized Spatiotemporal and Spatial Self-Attention for Action Recognition"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8561-660X","authenticated-orcid":false,"given":"Saghir","family":"Alfasly","sequence":"first","affiliation":[{"name":"Shenzhen Key Laboratory of Advanced Machine Learning and Applications, College of Mathematics and Statistics, Shenzhen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2482-8980","authenticated-orcid":false,"given":"Charles K.","family":"Chui","sequence":"additional","affiliation":[{"name":"Department of Statistics, Stanford University, Stanford, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0173-9988","authenticated-orcid":false,"given":"Qingtang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, University of Missouri–St. Louis, St. Louis, MO, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4599-7281","authenticated-orcid":false,"given":"Jian","family":"Lu","sequence":"additional","affiliation":[{"name":"Shenzhen Key Laboratory of Advanced Machine Learning and Applications, College of Mathematics and Statistics, Shenzhen University, Shenzhen, China"}]},{"given":"Chen","family":"Xu","sequence":"additional","affiliation":[{"name":"Shenzhen Key Laboratory of Advanced Machine Learning and Applications, College of Mathematics and Statistics, Shenzhen University, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"An image is worth $16 \\times 16$\n words: transformers for image recognition at scale","volume-title":"Proc. Comput. Vis. Pattern Recognit. (ICLR)","author":"Dosovitskiy"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref5","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Vaswani"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref7","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","volume-title":"Proc. ICML","volume":"139","author":"Bertasius"},{"key":"ref8","article-title":"An image is worth $16 \\times 16$\n words, what is a video worth?","author":"Sharir","year":"2021","journal-title":"arXiv:2103.13915"},{"key":"ref9","first-page":"19594","article-title":"Space-time mixing attention for video transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Bulat"},{"key":"ref10","article-title":"Video Swin transformer","author":"Liu","year":"2021","journal-title":"arXiv:2106.13230"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015848"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2882805"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3105184"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2791180"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2020.2971958"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2993901"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref21","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Simonyan"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref23","article-title":"Towards good practices for very deep two-stream ConvNets","author":"Wang","year":"2015","journal-title":"arXiv:1507.02159"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"ref26","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Patrick"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587730"},{"key":"ref28","volume-title":"Nvidia Ampere Ga102 GPU Architecture","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106995"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09004-3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3061115"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.12.007"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.08.003"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2745212"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2887021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2910208"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2019.2962815"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2907060"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3053765"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2785279"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2914137"},{"key":"ref42","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016","journal-title":"arXiv:1609.08675"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref44","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012","journal-title":"arXiv:1212.0402"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"ref47","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref49","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Paszke"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_21"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10422842\/09834306.pdf?arnumber=9834306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:15:25Z","timestamp":1708110925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9834306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":54,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3190367","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}