{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:34:08Z","timestamp":1787013248753,"version":"build-2736575974"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702390"],"award-info":[{"award-number":["61702390"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["JB181001"],"award-info":[{"award-number":["JB181001"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Research and Development Program of Shaanxi Province","award":["2018ZDXM-GY-036"],"award-info":[{"award-number":["2018ZDXM-GY-036"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1109\/tmm.2018.2869278","type":"journal-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T16:02:48Z","timestamp":1537545768000},"page":"1011-1021","source":"Crossref","is-referenced-by-count":104,"title":["Continuous Gesture Segmentation and Recognition Using 3DCNN and Convolutional LSTM"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3214-4095","authenticated-orcid":false,"given":"Guangming","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4331-5830","authenticated-orcid":false,"given":"Liang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peiyi","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2181-8445","authenticated-orcid":false,"given":"Syed Afaq Ali","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Depthwise separable convolutions for neural machine translation","author":"kaiser","year":"2017","journal-title":"arXiv 1706 03059"},{"key":"ref38","article-title":"Xception: Deep learning with depthwise separable convolutions","author":"chollet","year":"2016","journal-title":"arXiv 1610 02357"},{"key":"ref33","article-title":"Exploring temporal preservation networks for precise temporal action localization","author":"yang","year":"2017","journal-title":"arXiv 1708 03280"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3131343"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.377"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899609"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref36","article-title":"Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and imageNet","author":"hara","year":"2017","journal-title":"arXiv 1711 09577"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937674"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.155"},{"key":"ref27","first-page":"227","article-title":"Multi-layered gesture recognition with kinect","volume":"16","author":"jiang","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref29","article-title":"TPC: Temporal preservation convolutional networks for precise temporal action localization","author":"yang","year":"2017","journal-title":"arXiv 1708 03280"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.100"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2523421"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.371"},{"key":"ref22","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.369"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.678"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_36"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_33"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.456"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601260"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.08.063"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref10","first-page":"227","article-title":"Multi-layered gesture recognition with kinect","volume":"16","author":"jiang","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2374357"},{"key":"ref40","article-title":"Rethinking spatiotemporal feature learning for video understanding","author":"xie","year":"2017","journal-title":"arXiv 1712 04851"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2246148"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899606"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899600"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899603"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.361"},{"key":"ref18","article-title":"ConvNet architecture search for spatiotemporal feature learning","author":"tran","year":"2017","journal-title":"arXiv 1708 05038"},{"key":"ref19","first-page":"802","article-title":"Convolutional LSTM Network: A machine learning approach for precipitation nowcasting","author":"shi","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899599"},{"key":"ref3","first-page":"25","article-title":"Large-scale gesture recognition with a fusion of RGB-D data based on the C3D model","author":"li","year":"0","journal-title":"Proc 23rd Int Conf Pattern Recog"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2684186"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899601"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.360"},{"key":"ref7","article-title":"Multi-modality fusion based on consensus-voting and 3D convolution for isolated gesture recognition","author":"duan","year":"2016","journal-title":"arXiv 1611 06689"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0957-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2749509"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_35"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00549"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_34"},{"key":"ref42","first-page":"1","article-title":"Challenges in multimodal gesture recognition","volume":"17","author":"escalera","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref41","year":"2017"},{"key":"ref44","article-title":"Temporal relational reasoning in videos","author":"zhou","year":"2017","journal-title":"arXiv 1711 08496"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.370"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8672836\/08458185.pdf?arnumber=8458185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T16:50:18Z","timestamp":1657731018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8458185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":60,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2869278","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4]]}}}