{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T01:48:53Z","timestamp":1774057733434,"version":"3.50.1"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2016,8,1]],"date-time":"2016-08-01T00:00:00Z","timestamp":1470009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"name":"European Unions Horizon 2020 research and innovation programme"},{"name":"Marie Sklodowska-Curie","award":["657679"],"award-info":[{"award-number":["657679"]}]},{"DOI":"10.13039\/501100002347","name":"BMBF","doi-asserted-by":"publisher","award":["01GQ1115"],"award-info":[{"award-number":["01GQ1115"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61528106"],"award-info":[{"award-number":["61528106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2016,8,1]]},"DOI":"10.1109\/tpami.2016.2537340","type":"journal-article","created":{"date-parts":[[2016,3,2]],"date-time":"2016-03-02T19:14:03Z","timestamp":1456946043000},"page":"1583-1597","source":"Crossref","is-referenced-by-count":389,"title":["Deep Dynamic Neural Networks for Multimodal Gesture Segmentation and Recognition"],"prefix":"10.1109","volume":"38","author":[{"given":"Di","family":"Wu","sequence":"first","affiliation":[]},{"given":"Lionel","family":"Pigou","sequence":"additional","affiliation":[]},{"given":"Pieter-Jan","family":"Kindermans","sequence":"additional","affiliation":[]},{"given":"Nam Do-Hoang","family":"Le","sequence":"additional","affiliation":[]},{"given":"Ling","family":"Shao","sequence":"additional","affiliation":[]},{"given":"Joni","family":"Dambre","sequence":"additional","affiliation":[]},{"given":"Jean-Marc","family":"Odobez","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"665","article-title":"Convolutional-recursive deep learning for 3d object classification","author":"socher","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","author":"dosovitskiy","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/89.260359"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref30","first-page":"2929","article-title":"Actions in context","author":"marsza?ek","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref37","first-page":"1521","article-title":"Hidden conditional random fields for gesture recognition","volume":"2","author":"wang","year":"0","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recog"},{"key":"ref36","article-title":"Action points: A representation for low-latency online human action recognition","author":"nowozin","year":"2012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_40"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_39"},{"key":"ref60","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"0","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref62","first-page":"579","article-title":"Gesture recognition using template based random forest classifiers","author":"camg\u00f6z","year":"0","journal-title":"Proceedings of the Workshop on Visual Computing"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"ref63","first-page":"503","article-title":"Nonparametric gesture labeling from multi-modal data","author":"chang","year":"0","journal-title":"Proc Eur Conf Comput Vision Pattern Recog Workshops"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239178"},{"key":"ref64","first-page":"595","article-title":"Continuous gesture recognition from articulated poses","author":"evangelidis","year":"0","journal-title":"Proceedings of the Workshop on Visual Computing"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208303"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_43"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_44"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"ref67","article-title":"Theano: New features and speed improvements","author":"bastien","year":"0","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.137"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2273174"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.07.006"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref22","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.98"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"ref23","article-title":"Deepspeech: Scaling up end-to-end speech recognition","author":"hannun","year":"0","journal-title":"arXiv preprint arXiv 1412 5567"},{"key":"ref26","year":"2013","journal-title":"ACM ChaLearn Multi-Modal Gesture Recognition Grand Challenge and Workshop"},{"key":"ref25","first-page":"1317","article-title":"Enhanced computer vision with microsoft kinect sensor: A review","volume":"43","author":"han","year":"2013","journal-title":"IEEE Trans Cybern"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00044-3"},{"key":"ref51","first-page":"719","article-title":"A P300 BCI for the masses: Prior information enables instant unsupervised spelling","author":"kindermans","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref59","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"0","journal-title":"arXiv preprint arXiv 1207 0580"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"ref57","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"0","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref56","author":"yu","year":"2012","journal-title":"Automatic Speech Recognition"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2013.04.007"},{"key":"ref54","first-page":"137","article-title":"Motion templates for automatic classification and retrieval of motion capture data","author":"m\u00fcller","year":"0","journal-title":"Proc SIGGRAPH\/Eurographics Symp Comput Animat"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.153"},{"key":"ref52","article-title":"Learning deep generative models","author":"salakhutdinov","year":"2009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.124"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15567-3_11"},{"key":"ref40","first-page":"345","article-title":"Learning rich features from rgb-d images for object detection and segmentation","author":"gupta","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.124"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref16","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2203731"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88688-4_48"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"ref49","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref46","first-page":"491","article-title":"A multi-scale boosted detector for efficient and robust gesture recognition","author":"monnier","year":"0","journal-title":"Proc Eur Conf Comput Vis Pattern Recog Workshops"},{"key":"ref45","first-page":"474","article-title":"Multi-scale deep learning for gesture detection and localization","author":"neverova","year":"0","journal-title":"Proc Eur Conf Comput Vis Pattern Recog Workshops"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_36"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.67"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2532589"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2532593"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_32"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.69"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/iel7\/34\/7502203\/07423804.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/7502203\/07423804.pdf?arnumber=7423804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:27:00Z","timestamp":1642004820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7423804\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8,1]]},"references-count":68,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2016.2537340","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,8,1]]}}}