{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:24:49Z","timestamp":1780673089437,"version":"3.54.1"},"reference-count":108,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003407","name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003407","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1109\/tmm.2019.2960588","type":"journal-article","created":{"date-parts":[[2019,12,18]],"date-time":"2019-12-18T20:53:22Z","timestamp":1576702402000},"page":"2481-2496","source":"Crossref","is-referenced-by-count":83,"title":["2-D Skeleton-Based Action Recognition via Two-Branch Stacked LSTM-RNNs"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9437-6217","authenticated-orcid":false,"given":"Danilo","family":"Avola","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Cascio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luigi","family":"Cinque","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8425-6892","authenticated-orcid":false,"given":"Gian Luca","family":"Foresti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6942-4851","authenticated-orcid":false,"given":"Cristiano","family":"Massaroni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0091-7241","authenticated-orcid":false,"given":"Emanuele","family":"Rodola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.2297321"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126316"},{"key":"ref33","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","volume":"abs 1212 402","author":"soomro","year":"2012","journal-title":"ArXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408849"},{"key":"ref30","first-page":"181","article-title":"Action recognition in realistic sports videos","author":"soomro","year":"0","journal-title":"Computer Vision in Sports"},{"key":"ref37","first-page":"1","article-title":"C-RNN-GAN: A continuous recurrent neural network with adversarial training","author":"mogren","year":"0","journal-title":"Proceedings of the NIPS Workshop on Constructive Machine Learning"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"ref34","article-title":"The kinetics human action video dataset","volume":"abs 1705 6950","author":"kay","year":"2017","journal-title":"ArXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70711"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2759504"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2400218"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2887016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856094"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1049\/ic.2016.0063"},{"key":"ref26","first-page":"864","article-title":"Real-time compressive tracking","author":"zhang","year":"0","journal-title":"Proc Euro Conf Comput Vision"},{"key":"ref100","first-page":"527","article-title":"Shuffle and learn: Unsupervised learning using temporal order verification","author":"misra","year":"0","journal-title":"Proc Euro Conf Comput Vision"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00768"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2203742"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.215"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2791180"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.03.003"},{"key":"ref57","first-page":"97","article-title":"Attention-based temporal weighted convolutional neural network for action recognition","author":"zang","year":"0","journal-title":"Proc Innovative Applicat Artif Intell"},{"key":"ref56","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"0","journal-title":"Proc Euro Conf Comput Vision"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2678539"},{"key":"ref53","first-page":"457","article-title":"Dividing and aggregating network for multi-view action recognition","author":"wang","year":"0","journal-title":"Proc Euro Conf Comput Vision"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00539"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"1849","DOI":"10.1016\/j.patrec.2012.10.020","article-title":"Common-sense reasoning for human action recognition","volume":"34","author":"rinc\u00f3n","year":"2013","journal-title":"Pattern Recognit Lett"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.11.014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2838320"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.03.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-015-1066-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6875-7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.137"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.07.016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5730-1"},{"key":"ref46","first-page":"3378","article-title":"Incorporating contextual knowledge to dynamic Bayesian networks for event recognition","author":"wang","year":"0","journal-title":"Proc 21st Int Conf Pattern Recognit"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383074"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2816960"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2018.2850301"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126279"},{"key":"ref41","first-page":"610","article-title":"Event modeling and recognition using Markov logic networks","author":"tran","year":"0","journal-title":"Proc Euro Conf Comput Vision"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.08.002"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/j.cviu.2006.10.016","article-title":"Vision-based human motion analysis: An overview","volume":"108","author":"poppe","year":"2007","journal-title":"Comput Vision Image Understand"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"ref72","first-page":"2003","article-title":"Discriminative figure-centric models for joint action localization and recognition","author":"lan","year":"0","journal-title":"Proc Int Conf Comput Vision"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.09.001"},{"key":"ref70","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref77","first-page":"88","article-title":"Comparing evaluation protocols on the kth dataset","author":"gao","year":"0","journal-title":"Proc Int Conf Hum Behav Underst"},{"key":"ref74","first-page":"3882","article-title":"Phased LSTM: Accelerating recurrent network training for long or event-based sequences","author":"neil","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.08.014"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587721"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.217"},{"key":"ref62","first-page":"1110","article-title":"Hierarchical recurrent neural network for skeleton based action recognition","author":"du","year":"0","journal-title":"Proc Conf Comput Vis and Pattern Recog"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"ref63","first-page":"190","article-title":"Training and analyzing deep recurrent neural networks","author":"hermans","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref64","first-page":"338","article-title":"Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition","author":"sak","year":"0","journal-title":"Proc Int Speech Commun Assoc"},{"key":"ref65","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref66","article-title":"Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline)","author":"sun","year":"0","journal-title":"Proc Euro Conf Comput Vision"},{"key":"ref67","first-page":"385","article-title":"Idiot's bayes: Not so stupid after all?","volume":"69","author":"hand","year":"2007","journal-title":"Int Stat Rev"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2903448"},{"key":"ref69","first-page":"1","article-title":"Rectifier nonlinearities improve neural network acousticmodels","author":"maas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref95","first-page":"816","article-title":"Spatio-temporal LSTM with trust gates for 3D human action recognition","author":"liu","year":"0","journal-title":"Proc Euro Conf Comput Vision"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2015.2501981"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298934"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2898742"},{"key":"ref93","first-page":"529","article-title":"Gesture modeling by hanklet-based hidden Markov model","author":"presti","year":"0","journal-title":"Proc Asian Conf Comput Vision"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00539"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.78"},{"key":"ref105","first-page":"585","article-title":"Skeleton-based action recognition using LSTM and CNN","author":"li","year":"0","journal-title":"Proc Int Workshop Multimedia & Expo"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref103","first-page":"816","article-title":"Spatio-temporal LSTM with trust gates for 3D human action recognition","author":"liu","year":"0","journal-title":"Proc Euro Conf Comput Vision"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299172"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.76"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.772"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.98"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.108"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.11.012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2016.10.015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.029"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.06.011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.11.019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/M2VIP.2017.8211432"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/s17040805"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691768"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-016-0033-9"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.124"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2890749"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref88","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Int Conf Neural Inf Process"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9204776\/08936339.pdf?arnumber=8936339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:56:41Z","timestamp":1651075001000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8936339\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":108,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2960588","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}