{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T07:01:23Z","timestamp":1779174083485,"version":"3.51.4"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2018,5,1]],"date-time":"2018-05-01T00:00:00Z","timestamp":1525132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/tmm.2018.2818329","type":"journal-article","created":{"date-parts":[[2018,4,3]],"date-time":"2018-04-03T18:52:03Z","timestamp":1522781523000},"page":"1051-1061","source":"Crossref","is-referenced-by-count":155,"title":["Depth Pooling Based Large-Scale 3-D Action Recognition With Convolutional Neural Networks"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1430-0237","authenticated-orcid":false,"given":"Pichao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4427-2687","authenticated-orcid":false,"given":"Wanqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2450-492X","authenticated-orcid":false,"given":"Zhimin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip O.","family":"Ogunbona","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806296"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.104"},{"key":"ref33","first-page":"227","article-title":"Multi-layered gesture recognition with kinect","volume":"16","author":"jiang","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239179"},{"key":"ref31","first-page":"3297","article-title":"Human gesture recognition on product manifolds","volume":"13","author":"lui","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1973.9030"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.108"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.98"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396382"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1109\/TCSVT.2008.2005597","article-title":"Expandable data-driven\n graphical modeling of human actions based on salient postures","volume":"18","author":"li","year":"2008","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899603"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"ref61","first-page":"36","article-title":"Segmental spatiotemporal CNNS for fine-grained action\n segmentation","author":"lea","year":"0","journal-title":"Proc 14th Eur Conf Comput Vis"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2017.01.035"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2328181"},{"key":"ref27","first-page":"2549","article-title":"One-shot learning gesture recognition from RGB-D data\n using bag of features","volume":"14","author":"wan","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref29","first-page":"1","article-title":"Principal motion components for one-shot gesture recognition","author":"escalante","year":"2015","journal-title":"Pattern Anal Appl"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.04.011"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899599"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.05.007"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899600"},{"key":"ref24","first-page":"1","article-title":"Challenges\n in multimodal gesture recognition","volume":"17","author":"escalera","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.08.004"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.01.010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2469551"},{"key":"ref50","article-title":"Inverted residuals and linear bottlenecks: Mobile networks for\n classification, detection and segmentation","author":"sandler","year":"2018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-014-0596-3"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899606"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2513479"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899601"},{"key":"ref56","first-page":"25","article-title":"Large-scale gesture recognition with a fusion of RGB-D data\n based on the C3D model","author":"li","year":"0","journal-title":"Proc Int Workshop Pattern Recognit"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.52"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.244"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.23.2.023017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.418"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2015.2504550"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref13","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","author":"srivastava","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.212"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.100"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.05.019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.11.019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.460"},{"key":"ref5","first-page":"1110","article-title":"Hierarchical recurrent\n neural network for skeleton based action recognition","author":"du","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref8","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref7","first-page":"816","article-title":"Spatio-temporal LSTM with trust gates for 3D human\n action recognition","author":"liu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899609"},{"key":"ref9","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Ann Conf Neural Inf Process Syst"},{"key":"ref46","article-title":"Cooperative training of deep aggregation networks for RGB-D action recognition","author":"wang","year":"0","journal-title":"AAAI"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2628339"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref47","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.123"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537340"},{"key":"ref44","first-page":"102","article-title":"Action recognition based on joint trajectory\n maps using convolutional neural networks","author":"wang","year":"0","journal-title":"Proc ACM Int Conf Multimedia"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2782258"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8340086\/08330763.pdf?arnumber=8330763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T08:22:35Z","timestamp":1643185355000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8330763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":63,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2818329","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5]]}}}