{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T17:15:39Z","timestamp":1782062139863,"version":"3.54.5"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61762023"],"award-info":[{"award-number":["61762023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shaoguan Science and Technology Plan Project","award":["2019sn064"],"award-info":[{"award-number":["2019sn064"]}]},{"DOI":"10.13039\/501100006770","name":"Shaoguan University","doi-asserted-by":"publisher","award":["SY2018KJ03"],"award-info":[{"award-number":["SY2018KJ03"]}],"id":[{"id":"10.13039\/501100006770","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006770","name":"Shaoguan University","doi-asserted-by":"publisher","award":["SZ2016KJ09"],"award-info":[{"award-number":["SZ2016KJ09"]}],"id":[{"id":"10.13039\/501100006770","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006770","name":"Shaoguan University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006770","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2019.2962284","type":"journal-article","created":{"date-parts":[[2019,12,25]],"date-time":"2019-12-25T20:52:27Z","timestamp":1577307147000},"page":"1840-1850","source":"Crossref","is-referenced-by-count":47,"title":["Learning Long-Term Temporal Features With Deep Neural Networks for Human Action Recognition"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8302-462X","authenticated-orcid":false,"given":"Sheng","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3303-312X","authenticated-orcid":false,"given":"Li","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8919-3173","authenticated-orcid":false,"given":"Lin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daoxun","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref72","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref71","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00734"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.09.003"},{"key":"ref74","article-title":"Regularizing and optimizing LSTM language models","author":"merity","year":"2017","journal-title":"arXiv 1708 02182"},{"key":"ref39","first-page":"8698","article-title":"Hallucinating IDT descriptors and I3D optical flow features for action recognition with CNNs","author":"wang","year":"2019","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE.2018.8326195"},{"key":"ref38","article-title":"Convnet architecture search for spatiotemporal feature learning","author":"tran","year":"2017","journal-title":"arXiv 1708 05038"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2817253"},{"key":"ref79","article-title":"Multi-level recurrent residual networks for action recognition","author":"zheng","year":"2017","journal-title":"arXiv 1711 08238"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.03.005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref31","article-title":"Learning gating convnet for two-stream based methods in action recognition","author":"zhu","year":"2017","journal-title":"arXiv 1709 03655"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2892118"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref34","article-title":"Temporal 3D convnets: New architecture and transfer learning for video classification","author":"diba","year":"2017","journal-title":"arXiv 1711 08200"},{"key":"ref60","article-title":"A Bayesian hierarchical model for learning natural scene categories","author":"li","year":"2005","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref62","article-title":"MARS: Motion-augmented RGB stream for action recognition","author":"crasto","year":"2019","journal-title":"Proc IEEE Conf Comput Vis"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206709"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.028"},{"key":"ref28","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref27","article-title":"Towards good practices for very deep two-stream convnets","author":"wang","year":"2015","journal-title":"ArXiv 1507 02159"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964297"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2666540"},{"key":"ref29","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-51811-4_30"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2874022"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.172"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.03.002"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.235"},{"key":"ref20","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.604"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2010.10.002"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.332"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.04.015"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5244\/C.2.23"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"ref52","article-title":"Beyond spatial pyramid matching: Space-time extended descriptor for action recognition","author":"lan","year":"2015","journal-title":"arXiv 1510 04565"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.014"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.06.084"},{"key":"ref84","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","author":"gal","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref83","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2904857"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.219"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00234"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.333"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref86","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv preprint arXiv 1705 06950"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206821"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref48","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","author":"srivastava","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref47","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.09.007"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref43","article-title":"Supervised sequence labelling with recurrent neural networks","author":"kawakami","year":"2008"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08943218.pdf?arnumber=8943218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:50:27Z","timestamp":1639770627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8943218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2962284","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}