{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:37:52Z","timestamp":1768340272796,"version":"3.49.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3805901"],"award-info":[{"award-number":["2023YFC3805901"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172190"],"award-info":[{"award-number":["62172190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"\u201cDouble Creation\u201d Plan of Jiangsu Province"},{"name":"\u201cTaihu Talent-Innovative Leading Talent\u201d Plan of Wuxi City"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tcsvt.2024.3387933","type":"journal-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T17:34:03Z","timestamp":1712943243000},"page":"8148-8160","source":"Crossref","is-referenced-by-count":11,"title":["YOWOv3: A Lightweight Spatio-Temporal Joint Network for Video Action Detection"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8284-727X","authenticated-orcid":false,"given":"Anlei","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8157-7326","authenticated-orcid":false,"given":"Yinghui","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9548-4236","authenticated-orcid":false,"given":"Jinlong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9162-8551","authenticated-orcid":false,"given":"Tao","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}]},{"given":"Haomiao","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shaanxi Normal University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3135-0447","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100842"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00807"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref7","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Bertasius"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3216663"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00240"},{"key":"ref10","article-title":"You only watch once: A unified CNN architecture for real-time spatiotemporal action localization","author":"K\u00f6p\u00fckl\u00fc","year":"2019","journal-title":"arXiv:1911.06644"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3104226"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2887061"},{"key":"ref15","first-page":"7621","article-title":"VideoCapsuleNet: A simplified network for action detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Duarte"},{"key":"ref16","first-page":"464","article-title":"Actor-context-actor relation network for spatio-temporal action localization","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Pan"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3276979"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533300"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2953187"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3295432"},{"key":"ref24","first-page":"10758","article-title":"Consistency-based semi-supervised learning for object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","author":"Jeong"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2887283"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2923712"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00180"},{"key":"ref34","article-title":"YOWOv2: A stronger yet efficient multi-level detection framework for real-time spatio-temporal action detection","author":"Yang","year":"2023","journal-title":"arXiv:2302.06848"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096764"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/math11183848"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref38","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021","journal-title":"arXiv:2107.08430"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00721"},{"key":"ref40","volume-title":"Ultralytics GitHub Repository","year":"2023"},{"key":"ref41","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00089"},{"key":"ref45","article-title":"Interlaced sparse self-attention for semantic segmentation","author":"Huang","year":"2019","journal-title":"arXiv:1907.12273"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01226"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01323"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-54032-6_4"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10700029\/10497699.pdf?arnumber=10497699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:12:51Z","timestamp":1736453571000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10497699\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":51,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3387933","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}