{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T16:08:02Z","timestamp":1773418082802,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":["61672260"],"award-info":[{"award-number":["61672260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2923651","type":"journal-article","created":{"date-parts":[[2019,6,19]],"date-time":"2019-06-19T20:01:32Z","timestamp":1560974492000},"page":"82246-82255","source":"Crossref","is-referenced-by-count":37,"title":["R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7565-8024","authenticated-orcid":false,"given":"Quanle","family":"Liu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3799-1963","authenticated-orcid":false,"given":"Xiangjiu","family":"Che","sequence":"additional","affiliation":[]},{"given":"Mei","family":"Bie","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref38","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref33","article-title":"SlowFast networks for video recognition","author":"feichtenhofer","year":"2018","journal-title":"arXiv 1812 03982"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_18"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66179-7_27"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref35","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2014","journal-title":"Arxiv 1412 7755"},{"key":"ref34","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref40","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","first-page":"4278","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref16","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/135062800394667"},{"key":"ref19","first-page":"1243","article-title":"Learning to combine foveal glimpses with a third-order Boltzmann machine","author":"larochelle","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2011.2181865"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2894025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref29","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"Proc Adv Neu Inf Proc Sys"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2895472"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2778011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.168"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref24","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":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref43","article-title":"Convnet architecture search for spatiotemporal feature learning","author":"tran","year":"2017","journal-title":"arXiv 1708 05038"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08740848.pdf?arnumber=8740848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T19:39:56Z","timestamp":1628624396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8740848\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2923651","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}