{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:47:27Z","timestamp":1774540047732,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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":["62106158"],"award-info":[{"award-number":["62106158"]}],"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":["62206010"],"award-info":[{"award-number":["62206010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011347","name":"State Key Laboratory of Software Development Environment","doi-asserted-by":"publisher","award":["SKLSDE-2020KF-08"],"award-info":[{"award-number":["SKLSDE-2020KF-08"]}],"id":[{"id":"10.13039\/501100011347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003213","name":"Research and Development Program of Beijing Municipal Education Commission","doi-asserted-by":"publisher","award":["KM202210028007"],"award-info":[{"award-number":["KM202210028007"]}],"id":[{"id":"10.13039\/501100003213","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3250646","type":"journal-article","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T18:27:44Z","timestamp":1677695264000},"page":"5174-5185","source":"Crossref","is-referenced-by-count":34,"title":["Spatio-Temporal Adaptive Network With Bidirectional Temporal Difference for Action Recognition"],"prefix":"10.1109","volume":"33","author":[{"given":"Zhilei","family":"Li","sequence":"first","affiliation":[{"name":"Information Engineering College, Capital Normal University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5009-6536","authenticated-orcid":false,"given":"Jun","family":"Li","sequence":"additional","affiliation":[{"name":"Information Engineering College, Capital Normal University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1936-9396","authenticated-orcid":false,"given":"Yuqing","family":"Ma","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9848-7042","authenticated-orcid":false,"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"Information Engineering College, Capital Normal University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3562-8602","authenticated-orcid":false,"given":"Zhiping","family":"Shi","sequence":"additional","affiliation":[{"name":"Information Engineering College, Capital Normal University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3612-8757","authenticated-orcid":false,"given":"Yifu","family":"Ding","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8425-4195","authenticated-orcid":false,"given":"Xianglong","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","first-page":"2208","article-title":"Trajectory convolution for action recognition","author":"zhao","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref57","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00687"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00314"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018674"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01233"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01165"},{"key":"ref53","article-title":"A2 -Nets: Double attention networks","author":"chen","year":"2018","journal-title":"arXiv 1810 11579"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2203731"},{"key":"ref55","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref10","first-page":"1","article-title":"Real-time hand gesture detection and classification using convolutional neural networks","author":"kopuklu","year":"2019","journal-title":"Proc 14th IEEE Int Conf Autom Face Gesture Recognit (FG)"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_24"},{"key":"ref19","first-page":"214","article-title":"A duality based approach for realtime TV-L1 optical flow","author":"zach","year":"2007","journal-title":"Proc DAGM-Symp Pattern Recognition"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2512107"},{"key":"ref51","first-page":"1","article-title":"Spatial transformer networks","volume":"28","author":"jaderberg","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018401"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00123"},{"key":"ref41","first-page":"305","article-title":"Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification","author":"xie","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref43","article-title":"Temporal 3D ConvNets: New architecture and transfer learning for video classification","author":"diba","year":"2017","journal-title":"arXiv 1711 08200"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3142771"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3098839"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3019293"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2628339"},{"key":"ref40","first-page":"695","article-title":"ECO: Efficient convolutional network for online video understanding","author":"zolfaghari","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref33","article-title":"A dataset of 101 human action classes from videos in the wild","volume":"2","author":"soomro","year":"2012","journal-title":"Computer and Vision Research Center"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref2","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Conf Workshop Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2785279"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_36"},{"key":"ref63","article-title":"TSI: Temporal saliency integration for video action recognition","author":"su","year":"2021","journal-title":"arXiv 2106 01088"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107037"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_17"},{"key":"ref28","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01465"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180585"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/148"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10057034.pdf?arnumber=10057034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:40:59Z","timestamp":1695667259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10057034\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":67,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3250646","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}