{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:17:34Z","timestamp":1785421054205,"version":"3.56.0"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Amazon AWS through the Oxford-Singapore Human-Machine Collaboration Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tnnls.2022.3175480","type":"journal-article","created":{"date-parts":[[2022,5,27]],"date-time":"2022-05-27T20:57:57Z","timestamp":1653685077000},"page":"451-465","source":"Crossref","is-referenced-by-count":12,"title":["Multiscale Human Activity Recognition and Anticipation Network"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3786-2865","authenticated-orcid":false,"given":"Yang","family":"Xing","sequence":"first","affiliation":[{"name":"Centre for Autonomous and Cyber-Physical Systems, Cranfield University, Cranfield, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stuart","family":"Golodetz","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxford, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aluna","family":"Everitt","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxford, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5716-3941","authenticated-orcid":false,"given":"Andrew","family":"Markham","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxford, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6236-9645","authenticated-orcid":false,"given":"Niki","family":"Trigoni","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxford, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2363664"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103199"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2572698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.11.014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2976014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3076172"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.115"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00947"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.610"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70731"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093457"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2874455"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2015.00028"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.02.002"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2017.8016048"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989778"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref19","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"issue":"9","key":"ref21","first-page":"2508","article-title":"Survey of convolutional neural network","volume":"36","author":"Li","year":"2565","journal-title":"J. Comput. Appl."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/34.868685"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2564404"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.032"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.25"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2611485"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref38","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2018.2875079"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref42","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2883741"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref46","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00539"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/COGSIMA.2017.7929606"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat1587"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460924"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.39"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.2297321"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00151"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01016"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11015-4_10"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00566"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059923"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01486-4"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.209"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_48"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"ref78","article-title":"PERF-Net: Pose empowered RGB-flow net","author":"Li","year":"2020","journal-title":"arXiv:2009.13087"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00807"},{"key":"ref80","article-title":"Attention is all we need: Nailing down object-centric attention for egocentric activity recognition","author":"Sudhakaran","year":"2018","journal-title":"arXiv:1807.11794"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412148"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2011.5940538"},{"key":"ref84","article-title":"Brain4Cars: Car that knows before you do via sensory-fusion deep learning architecture","author":"Jain","year":"2016","journal-title":"arXiv:1601.00740"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814249"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref87","article-title":"Video swin transformer","author":"Liu","year":"2021","journal-title":"arXiv:2106.13230"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10381493\/09783453.pdf?arnumber=9783453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:04:05Z","timestamp":1705025045000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9783453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":87,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3175480","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}