{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T11:48:42Z","timestamp":1774352922524,"version":"3.50.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2018,7,1]],"date-time":"2018-07-01T00:00:00Z","timestamp":1530403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772043"],"award-info":[{"award-number":["61772043"]}],"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":["61672519"],"award-info":[{"award-number":["61672519"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004318","name":"Microsoft Research Asia Fund","doi-asserted-by":"publisher","award":["FY17-RES-THEME-013"],"award-info":[{"award-number":["FY17-RES-THEME-013"]}],"id":[{"id":"10.13039\/100004318","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Tencent Open Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/tip.2018.2818328","type":"journal-article","created":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T18:06:58Z","timestamp":1521742018000},"page":"3459-3471","source":"Crossref","is-referenced-by-count":235,"title":["Spatio-Temporal Attention-Based LSTM Networks for 3D Action Recognition and Detection"],"prefix":"10.1109","volume":"27","author":[{"given":"Sijie","family":"Song","sequence":"first","affiliation":[]},{"given":"Cuiling","family":"Lan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6801-0510","authenticated-orcid":false,"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0468-9576","authenticated-orcid":false,"given":"Jiaying","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.393"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.100"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.65"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.101"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.387"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2014.6890714"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.772"},{"key":"ref28","first-page":"2","article-title":"Action recognition and detection by combining motion and appearance features","volume":"1","author":"wang","year":"2014","journal-title":"THUMOS Action Recognition challenge"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299172"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref29","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2010.10.002"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.11.014"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.109"},{"key":"ref22","author":"liu","year":"2017","journal-title":"PKU-MMD A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding"},{"key":"ref21","first-page":"7","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 Conf Artif Intell"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.10.004"},{"key":"ref23","first-page":"50","article-title":"Discriminative orderlet mining for real-time recognition of human-object interaction","author":"yu","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref26","first-page":"5","article-title":"Fast saliency based pooling of fisher encoded dense trajectories","volume":"1","author":"karaman","year":"2014","journal-title":"Proc European Conf Comp Vis Workshop"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.342"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"ref58","author":"zaremba","year":"2014","journal-title":"Recurrent Neural Network Regularization"},{"key":"ref57","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248012"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref52","article-title":"Gradient flow in recurrent nets: The difficulty of learning long-term dependencies","author":"hochreiter","year":"2001","journal-title":"A Field Guide to Dynamical Recurrent Neural Networks"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2799968"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.04.005"},{"key":"ref13","first-page":"8","article-title":"Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks","author":"zhu","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.07.014"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_13"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2552404"},{"key":"ref18","first-page":"1","article-title":"Temporal perceptive network for skeleton-based action recognition","author":"hu","year":"2017","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref19","first-page":"1","article-title":"Action recognition by shape matching to key frames","volume":"1","author":"carlsson","year":"2001","journal-title":"Proc Workshop Models Versus Exemplars Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2331759"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2456412"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3758\/BF03212378"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2490551"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.24"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.01.011"},{"key":"ref49","first-page":"1","article-title":"Every moment counts: Dense detailed labeling of actions in complex videos","volume":"126","author":"yeung","year":"2017","journal-title":"Int J Comput Vis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"ref46","first-page":"1","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref45","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"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.332"},{"key":"ref47","first-page":"1","article-title":"Action recognition using visual attention","author":"sharma","year":"2016","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"1398","DOI":"10.1109\/TSMCB.2009.2038895","article-title":"An object-based visual attention model for robotic applications","volume":"40","author":"yu","year":"2010","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.272"},{"key":"ref44","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref43","first-page":"1","article-title":"Recurrent mixture density network for spatiotemporal visual attention","author":"bazzani","year":"2017","journal-title":"Proc Int Conf Learn Represent"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8332914\/08322061.pdf?arnumber=8322061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:15:52Z","timestamp":1642004152000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8322061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":65,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tip.2018.2818328","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7]]}}}