{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:23:48Z","timestamp":1767705828856,"version":"3.37.3"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"New York State through Snap"},{"name":"Cheetah Mobile"},{"DOI":"10.13039\/100005446","name":"Division of Institution and Award Support","doi-asserted-by":"publisher","award":["1704309"],"award-info":[{"award-number":["1704309"]}],"id":[{"id":"10.13039\/100005446","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":[[2019,8]]},"DOI":"10.1109\/tcsvt.2018.2864148","type":"journal-article","created":{"date-parts":[[2018,8,7]],"date-time":"2018-08-07T19:23:20Z","timestamp":1533669800000},"page":"2405-2415","source":"Crossref","is-referenced-by-count":137,"title":["Action Recognition With Spatio\u2013Temporal Visual Attention on Skeleton Image Sequences"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5808-0889","authenticated-orcid":false,"given":"Zhengyuan","family":"Yang","sequence":"first","affiliation":[]},{"given":"Yuncheng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jianchao","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"7444","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","author":"yan","year":"2018","journal-title":"Proc AAAI"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2815744"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.115"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511"},{"key":"ref37","first-page":"445","author":"weng","year":"2017","journal-title":"Spatio-temporal naive-bayes nearest-neighbor (st-nbnn) for skeleton-based action recognition"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.137"},{"key":"ref35","first-page":"4263","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","author":"song","year":"2017","journal-title":"Proc AAAI"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref28","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","year":"2014","author":"simonyan","key":"ref27"},{"key":"ref29","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546012"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_38"},{"key":"ref23","first-page":"428","article-title":"Human detection using oriented histograms of flow and appearance","author":"dalal","year":"2006","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref26","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.03.013"},{"journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild","year":"2012","author":"soomro","key":"ref50"},{"journal-title":"The kinetics human action video dataset","year":"2017","author":"kay","key":"ref51"},{"key":"ref58","first-page":"2078","article-title":"Self-paced learning with diversity","author":"jiang","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654918"},{"key":"ref56","first-page":"1189","article-title":"Self-paced learning for latent variable models","author":"kumar","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(00)00146-1"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.280"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239232"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"ref12","first-page":"1110","article-title":"Hierarchical recurrent neural network for skeleton based action recognition","author":"du","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.387"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.486"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.207"},{"key":"ref18","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"journal-title":"Action recognition using visual attention","year":"2015","author":"sharma","key":"ref19"},{"key":"ref4","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073596"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2398356.2398381"},{"journal-title":"Recurrent Neural Network Regularization","year":"2014","author":"zaremba","key":"ref49"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296256"},{"key":"ref46","first-page":"231","article-title":"Visual sentiment analysis by attending on local image regions","author":"you","year":"2017","journal-title":"Proc AAAI"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref48","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"newell","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"journal-title":"Skepxels Spatio-temporal image representation of human skeleton joints for action recognition","year":"2017","author":"liu","key":"ref41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.402"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/8786781\/08428616.pdf?arnumber=8428616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:12:03Z","timestamp":1657746723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8428616\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":58,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2018.2864148","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2019,8]]}}}