{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T18:50:43Z","timestamp":1762023043957,"version":"build-2065373602"},"reference-count":36,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2020,6,1]]},"DOI":"10.1587\/transinf.2019mvp0012","type":"journal-article","created":{"date-parts":[[2020,5,31]],"date-time":"2020-05-31T22:10:00Z","timestamp":1590963000000},"page":"1217-1225","source":"Crossref","is-referenced-by-count":3,"title":["Deep State-Space Model for Noise Tolerant Skeleton-Based Action Recognition"],"prefix":"10.1587","volume":"E103.D","author":[{"given":"Kazuki","family":"KAWAMURA","sequence":"first","affiliation":[{"name":"Faculty of Engineering and the Graduate School of System Informatics, Kobe University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"MATSUBARA","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and the Graduate School of System Informatics, Kobe University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuniaki","family":"UEHARA","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and the Graduate School of System Informatics, Kobe University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"doi-asserted-by":"publisher","unstructured":"[1] L.L. Presti and M.L. Cascia, \u201c3D skeleton-based human action classi fi cation: A survey,\u201d Pattern Recognition, vol.53, pp.130-147, 2016. 10.1016\/j.patcog.2015.11.019","key":"1","DOI":"10.1016\/j.patcog.2015.11.019"},{"doi-asserted-by":"publisher","unstructured":"[2] Z. Zhang, \u201cMicrosoft kinect sensor and its effect,\u201d IEEE Multimedia Mag., vol.19, no.2, pp.4-10, 2012. 10.1109\/mmul.2012.24","key":"2","DOI":"10.1109\/MMUL.2012.24"},{"doi-asserted-by":"crossref","unstructured":"[3] J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, R. Moore, A. Kipman, and A. Blake, \u201cReal-Time Human Pose Recognition in Parts from Single Depth Images,\u201d IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011. 10.1109\/cvpr.2011.5995316","key":"3","DOI":"10.1109\/CVPR.2011.5995316"},{"doi-asserted-by":"crossref","unstructured":"[4] L. Xia, C.-C. Chen, and J.K. Aggarwal, \u201cView invariant human action recognition using histograms of 3d joints,\u201d CVPRW, 2012. 10.1109\/cvprw.2012.6239233","key":"4","DOI":"10.1109\/CVPRW.2012.6239233"},{"doi-asserted-by":"publisher","unstructured":"[5] X. Yang and Y. Tian, \u201cEffective 3D action recognition using EigenJoints,\u201d J Vis Commun Image Represent, vol.25, no.1, pp.2-11, 2014. 10.1016\/j.jvcir.2013.03.001","key":"5","DOI":"10.1016\/j.jvcir.2013.03.001"},{"doi-asserted-by":"crossref","unstructured":"[6] G. Evangelidis, G. Singh, and R. Horaud, \u201cSkeletal quads: Human action recognition using joint quadruples,\u201d International Conference on Pattern Recognition (ICPR), pp.4513-4518, 2014. 10.1109\/icpr.2014.772","key":"6","DOI":"10.1109\/ICPR.2014.772"},{"doi-asserted-by":"crossref","unstructured":"[7] R. Vemulapalli, F. Arrate, and R. Chellappa, \u201cHuman action recognition by representing 3D skeletons as points in a lie group,\u201d IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.588-595, 2014. 10.1109\/cvpr.2014.82","key":"7","DOI":"10.1109\/CVPR.2014.82"},{"unstructured":"[8] Y. Du, W. Wang, and L. Wang, \u201cHierarchical recurrent neural network for skeleton based action recognition,\u201d IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1110-1118, 2015. 10.1109\/cvpr.2015.7298714","key":"8"},{"doi-asserted-by":"crossref","unstructured":"[9] A. Shahroudy, J. Liu, T.-T. Ng, and G. Wang, \u201cNTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis,\u201d IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1010-1019, 2016. 10.1109\/cvpr.2016.115","key":"9","DOI":"10.1109\/CVPR.2016.115"},{"doi-asserted-by":"crossref","unstructured":"[10] J. Liu, A. Shahroudy, D. Xu, and G. Wang, \u201cSpatio-temporal lstm with trust gates for 3d human action recognition,\u201d ECCV, vol.9907, pp.816-833, 2016. 10.1007\/978-3-319-46487-9_50","key":"10","DOI":"10.1007\/978-3-319-46487-9_50"},{"unstructured":"[11] I.J. Goodfellow, J. Shlens, and C. Szegedy, \u201cExplaining and Harnessing Adversarial Examples,\u201d International Conference on Learning Representations (ICLR), 2015.","key":"11"},{"unstructured":"[12] A.Y. Ng, M.I. Jordan, A.Y.N. Jordan, and M. I., \u201cOn Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes,\u201d Advances in Neural Information Processing Systems (NIPS), pp.841-848, 2001.","key":"12"},{"unstructured":"[13] Y. Li, J. Bradshaw, and Y. Sharma, \u201cAre Generative Classifiers More Robust to Adversarial Attacks?,\u201d ICMLW, 2018.","key":"13"},{"unstructured":"[14] D.P. Kingma and M. Welling, \u201cAuto-encoding variational Bayes,\u201d International Conference on Learning Representations (ICLR), 2014.","key":"14"},{"unstructured":"[15] D.J. Rezende, S. Mohamed, and D. Wierstra, \u201cStochastic backpropagation and approximate inference in deep generative models,\u201d Proceedings of the 31st International Conference on Machine Learning (ICML), pp.1278-1286, PMLR, 2014.","key":"15"},{"unstructured":"[16] D. Im, S. Ahn, R. Memisevic, and Y. Bengio, \u201cDenoising criterion for variational auto-encoding framework,\u201d pp.2059-2065, 11 2017.","key":"16"},{"doi-asserted-by":"publisher","unstructured":"[17] J.L. Elman, \u201cFinding Structure in Time,\u201d Cognitive Science, vol.14, no.2, pp.179-211, 1990. 10.1207\/s15516709cog1402_1","key":"17","DOI":"10.1207\/s15516709cog1402_1"},{"doi-asserted-by":"publisher","unstructured":"[18] S. Hochreiter and J. Schmidhuber, \u201cLong short-term memory,\u201d Neural Computation, vol.9, no.8, pp.1735-1780, 1997. 10.1162\/neco.1997.9.8.1735","key":"18","DOI":"10.1162\/neco.1997.9.8.1735"},{"doi-asserted-by":"crossref","unstructured":"[19] K. Fukushima and S. Miyake, \u201cNeocognitron: a new algorithm for pattern recognition tolerant of deformations and shifts in position,\u201d Biological Cybernetics, vol.15, no.6, pp.455-469, 1982. 10.1016\/0031-3203(82)90024-3","key":"19","DOI":"10.1016\/0031-3203(82)90024-3"},{"doi-asserted-by":"crossref","unstructured":"[20] V. Veeriah, N. Zhuang, and G.-J. Qi, \u201cDifferential Recurrent Neural Networks for Action Recognition,\u201d International Conference on Computer Vision (ICCV), 2015. 10.1109\/iccv.2015.460","key":"20","DOI":"10.1109\/ICCV.2015.460"},{"doi-asserted-by":"crossref","unstructured":"[21] W. Zhu, C. Lan, J. Xing, W. Zeng, Y. Li, L. Shen, and X. Xie, \u201cCo-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks,\u201d AAAI Conference on Artificial Intelligence (AAAI), 2016.","key":"21","DOI":"10.1609\/aaai.v30i1.10451"},{"unstructured":"[22] J. Bayer and C. Osendorfer, \u201cLearning stochastic recurrent networks,\u201d arXiv preprint, 2015.","key":"22"},{"unstructured":"[23] C. Junyoung, K. Kyle, D. Laurent, G. Kratarth, C. Aaron, and B. Yoshua, \u201cA Recurrent Latent Variable Model for Sequential Data,\u201d Advances in Neural Information Processing Systems (NIPS), pp.2962-2970, 2015.","key":"23"},{"unstructured":"[24] M. Fraccaro, S.K. S\u00f8nderby, U. Paquet, and O. Winther, \u201cSequential Neural Models with Stochastic Layers,\u201d Advances in Neural Information Processing Systems (NIPS), pp.2199-2207, 2016.","key":"24"},{"unstructured":"[25] A. Goyal, A. Sordoni, and N.R. Ke, \u201cZ-Forcing: Training Stochastic Recurrent Networks,\u201d Advances in Neural Information Processing Systems (NIPS), pp.6713-6723, 2017.","key":"25"},{"unstructured":"[26] R.G. Krishnan, U. Shalit, and D. Sontag, \u201cStructured Inference Networks for Nonlinear State Space Models,\u201d AAAI Conference on Artificial Intelligence (AAAI), pp.2101-2109, 2017.","key":"26"},{"unstructured":"[27] M. Fraccaro, S. Kamronn, U. Paquet, and O. Winther, \u201cA disentangled recognition and nonlinear dynamics model for unsupervised learning,\u201d in Advances in Neural Information Processing Systems (NIPS), pp.3601-3610, 2017.","key":"27"},{"unstructured":"[28] S.S. Rangapuram, M.W. Seeger, J. Gasthaus, L. Stella, Y. Wang, and T. Januschowski, \u201cDeep state space models for time series forecasting,\u201d in Advances in Neural Information Processing Systems 31 (NIPS), ed. S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, pp.7785-7794, 2018.","key":"28"},{"doi-asserted-by":"crossref","unstructured":"[29] K. Cho, B. van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, \u201cLearning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation,\u201d Conference on Empirical Methods in Natural Language Processing (EMNLP), pp.1724-1734, 2014. 10.3115\/v1\/d14-1179","key":"29","DOI":"10.3115\/v1\/D14-1179"},{"unstructured":"[30] G. Hinton, \u201cDropout: A Simple Way to Prevent Neural Networks from Overfitting,\u201d Journal of Machine Learning Research (JMLR), pp.1929-1958, 2014.","key":"30"},{"unstructured":"[31] X. Glorot and A. Bordes, \u201cDeep Sparse Rectifier Neural Networks,\u201d International Conference on Artificial Intelligence and Statistics (AISTATS), pp.315-323, 2011.","key":"31"},{"unstructured":"[32] D.P. Kingma and J.L. Ba, \u201cAdam: A method for stochastic optimization,\u201d International Conference on Learning Representations (ICLR), 2015.","key":"32"},{"unstructured":"[33] J.-F. Hu, W.-S. Zheng, J. Lai, and J. Zhang, \u201cJointly Learning Heterogeneous Features for RGB-D Activity Recognition,\u201d IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.5344-5352, 2015. 10.1109\/cvpr.2015.7299172","key":"33"},{"doi-asserted-by":"crossref","unstructured":"[34] S. Song, C. Lan, J. Xing, W. Zeng, and J. Liu, \u201cAn End-to-End Spatio-Temporal Attention Model for Human Action Recognition,\u201d AAAI Conference on Artificial Intelligence (AAAI), 2017.","key":"34","DOI":"10.1609\/aaai.v31i1.11212"},{"doi-asserted-by":"crossref","unstructured":"[35] P. Zhang, C. Lan, J. Xing, W. Zeng, J. Xue, and N. Zheng, \u201cView Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data,\u201d International Conference on Computer Vision (ICCV), pp.2117-2126, 2017. 10.1109\/iccv.2017.233","key":"35","DOI":"10.1109\/ICCV.2017.233"},{"doi-asserted-by":"crossref","unstructured":"[36] S. Yan, Y. Xiong, and D. Lin, \u201cSpatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition,\u201d AAAI Conference on Artificial Intelligence (AAAI), 2018.","key":"36","DOI":"10.1609\/aaai.v32i1.12328"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E103.D\/6\/E103.D_2019MVP0012\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,25]],"date-time":"2022-10-25T21:40:28Z","timestamp":1666734028000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E103.D\/6\/E103.D_2019MVP0012\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,1]]},"references-count":36,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2019mvp0012","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2020,6,1]]}}}