{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T11:56:37Z","timestamp":1792324597262,"version":"4.4.0"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore, through the Interactive Digital Media Strategic Research Programme","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"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":["61661146005"],"award-info":[{"award-number":["61661146005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2016YFB1001501"],"award-info":[{"award-number":["2016YFB1001501"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/tip.2017.2785279","type":"journal-article","created":{"date-parts":[[2017,12,19]],"date-time":"2017-12-19T14:25:59Z","timestamp":1513693559000},"page":"1586-1599","source":"Crossref","is-referenced-by-count":546,"title":["Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4365-4165","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4491-2023","authenticated-orcid":false,"given":"Ling-Yu","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamila","family":"Abdiyeva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex C.","family":"Kot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2013.6474999"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299172"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_2"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.772"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967191"},{"key":"ref74","first-page":"1","article-title":"Torch7: A MATLAB-like environment for machine learning","author":"collobert","year":"2011","journal-title":"Proc NIPSW"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472170"},{"key":"ref75","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2014.6836044"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2690339"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505295"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.227"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref30","first-page":"1","article-title":"Memory networks","author":"weston","year":"2015","journal-title":"Proc ICLR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.218"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.334"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2013.03.001"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7284883"},{"key":"ref60","first-page":"1","article-title":"Action recognition using visual attention","author":"sharma","year":"2016","journal-title":"Proc ICLR"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref61","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","author":"kumar","year":"2016","journal-title":"Proc ICML"},{"key":"ref63","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Proc NIPS"},{"key":"ref28","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"},{"key":"ref64","first-page":"3545","article-title":"Deep networks with internal selective attention through feedback connections","author":"stollenga","year":"2014","journal-title":"Proc NIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref66","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc NIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"ref68","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":"ref69","author":"wang","year":"2016","journal-title":"Hierarchical attention network for action recognition in videos"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2512107"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2548242"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref24","author":"ke","year":"2017","journal-title":"Leveraging structural context models and ranking score fusion for human interaction prediction"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref26","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"2015","journal-title":"Proc ICML"},{"key":"ref25","author":"ke","year":"2016","journal-title":"Leveraging structural context models and ranking score fusion for human interaction prediction"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.01.020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_3"},{"key":"ref59","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"Proc ICML"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_13"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2771306"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.460"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.342"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_23"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.05.019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-44964-2_8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.48"},{"key":"ref12","first-page":"1110","article-title":"Hierarchical recurrent neural network for skeleton based action recognition","author":"du","year":"2015","journal-title":"Proc CVPR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2015.02.004"},{"key":"ref14","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref15","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2350774"},{"key":"ref16","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.08.011"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref84","first-page":"3604","article-title":"Recognizing actions in 3d using action-snippets and activated simplices","author":"wang","year":"2016","journal-title":"Proc AAAI"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"194","DOI":"10.21437\/Interspeech.2012-65","article-title":"LSTM neural networks for language modeling","author":"sundermeyer","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.289"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.217"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_17"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2014.04.007"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1318","DOI":"10.1109\/TCYB.2013.2265378","article-title":"Enhanced computer vision with microsoft kinect sensor: A review","volume":"43","author":"han","year":"2013","journal-title":"IEEE Trans Cybern"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2456412"},{"key":"ref6","first-page":"304","article-title":"Robust real-time human perception with depth camera","author":"zhang","year":"2016","journal-title":"Proc ECAI"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2731952"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.505"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.01.011"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2014.6890714"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.11.019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.198"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/NCVPRIPG.2013.6776204"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ISSNIP.2014.6827664"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.04.011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.153"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2014.7008115"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISCCSP.2014.6877819"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298934"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2013.04.007"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8246756\/08226767.pdf?arnumber=8226767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T22:04:26Z","timestamp":1693346666000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8226767\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":89,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tip.2017.2785279","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,4]]}}}