{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T22:06:27Z","timestamp":1781215587903,"version":"3.54.1"},"publisher-location":"Cham","reference-count":188,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319570204","type":"print"},{"value":"9783319570211","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-57021-1_19","type":"book-chapter","created":{"date-parts":[[2017,7,19]],"date-time":"2017-07-19T04:43:44Z","timestamp":1500439424000},"page":"539-578","source":"Crossref","is-referenced-by-count":38,"title":["Deep Learning for Action and Gesture Recognition in Image Sequences: A Survey"],"prefix":"10.1007","author":[{"given":"Maryam","family":"Asadi-Aghbolaghi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Albert","family":"Clap\u00e9s","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Bellantonio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugo Jair","family":"Escalante","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"V\u00edctor","family":"Ponce-L\u00f3pez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Bar\u00f3","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isabelle","family":"Guyon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shohreh","family":"Kasaei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0617-8873","authenticated-orcid":false,"given":"Sergio","family":"Escalera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,7,20]]},"reference":[{"key":"19_CR1","unstructured":"M.\u00a0Abadi, A.\u00a0Agarwal, P.\u00a0Barham, E.\u00a0Brevdo, Z.\u00a0Chen, C.\u00a0Citro, G.S. Corrado, A.\u00a0Davis, J.\u00a0Dean, M.\u00a0Devin, S.\u00a0Ghemawat, I.\u00a0Goodfellow, A.\u00a0Harp, G.\u00a0Irving, M.\u00a0Isard, Y.\u00a0Jia, R.\u00a0Jozefowicz, L.\u00a0Kaiser, M.\u00a0Kudlur, J.\u00a0Levenberg, D.\u00a0Man\u00e9, R.\u00a0Monga, S.\u00a0Moore, C.\u00a0Olah, M.\u00a0Schuster, J.\u00a0Shlens, B.\u00a0Steiner, I.\u00a0Sutskever, K.\u00a0Talwar, P.\u00a0Tucker, V.\u00a0Vanhoucke, V.\u00a0Vasudevan, F.\u00a0Vi\u00e9gas, O.\u00a0Vinyals, P.\u00a0Warden, M.\u00a0Wattenberg, M.\u00a0Wicke, Y.\u00a0Yu, X.\u00a0Zheng, TensorFlow: large-scale machine learning on heterogeneous systems, 2015a, http:\/\/tensorflow.org\/"},{"key":"19_CR2","unstructured":"M.\u00a0Abadi, A.\u00a0Agarwal, P.\u00a0Barham, E.\u00a0Brevdo, Z.\u00a0Chen, C.\u00a0Citro, G.S. Corrado, A.\u00a0Davis, J.\u00a0Dean, M.\u00a0Devin, et\u00a0al., Tensorflow: large-scale machine learning on heterogeneous systems, 2015b, http:\/\/www.tensorflow.org"},{"key":"19_CR3","unstructured":"S.\u00a0Abu-El-Haija, N.\u00a0Kothari, J.\u00a0Lee, P.\u00a0Natsev, G.\u00a0Toderici, B.\u00a0Varadarajan, S.\u00a0Vijayanarasimhan, Youtube-8m: a large-scale video classification benchmark. CoRR, abs\/1609.08675 (2016)"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"E.\u00a0Ahmed, M.\u00a0Jones, T.K. Marks, An improved deep learning architecture for person re-identification, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3908\u20133916","DOI":"10.1109\/CVPR.2015.7299016"},{"key":"19_CR5","unstructured":"R.\u00a0Al-Rfou, G.\u00a0Alain, A.\u00a0Almahairi, C.\u00a0Angermueller, D.\u00a0Bahdanau, N.\u00a0Ballas, F.\u00a0Bastien, J.\u00a0Bayer, A.\u00a0Belikov, et\u00a0al., Theano: a python framework for fast computation of mathematical expressions, 2016, arXiv:1605.02688"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"M.R. Amer, S.\u00a0Todorovic, A.\u00a0Fern, S.-C. Zhu, Monte carlo tree search for scheduling activity recognition, in Proceedings of the IEEE International Conference on Computer Vision, 2013, pp. 1353\u20131360","DOI":"10.1109\/ICCV.2013.171"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"R.\u00a0Araujo, M.S. Kamel, A semi-supervised temporal clustering method for facial emotion analysis, in 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), IEEE, 2014, pp. 1\u20136","DOI":"10.1109\/ICMEW.2014.6890712"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"K.\u00a0Avgerinakis, K.\u00a0Adam, A.\u00a0Briassouli, Y.\u00a0Kompatsiaris, Moving camera human activity localization and recognition with motionplanes and multiple homographies, in ICIP, IEEE, 2015, pp. 2085\u20132089","DOI":"10.1109\/ICIP.2015.7351168"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"M.\u00a0Baccouche, F.\u00a0Mamalet, C.\u00a0Wolf, C.\u00a0Garcia, A.\u00a0Baskurt, Action classification in soccer videos with long short-term memory recurrent neural networks, in International Conference on Artificial Neural Networks (Springer, Berlin, 2010), pp. 154\u2013159","DOI":"10.1007\/978-3-642-15822-3_20"},{"key":"19_CR10","first-page":"29","volume-title":"Sequential deep learning for human action recognition, in International Workshop on Human Behavior Understanding","author":"M Baccouche","year":"2011","unstructured":"M. Baccouche, F. Mamalet, C. Wolf, C. Garcia, A. Baskurt, Sequential deep learning for human action recognition, in International Workshop on Human Behavior Understanding (Springer, New York, 2011), pp. 29\u201339"},{"key":"19_CR11","unstructured":"N.\u00a0Ballas, L.\u00a0Yao, A.\u00a0Courville, Delving deeper into convolutional networks for learning video representations, in Proceedings of International Conference on Learning Representations, 2016"},{"key":"19_CR12","doi-asserted-by":"publisher","unstructured":"I.\u00a0Bayer, T.\u00a0Silbermann. A multi modal approach to gesture recognition from audio and video data, in ICMI (2013), pp. 461\u2013466. ISBN 978-1-4503-2129-7. doi: 10.1145\/2522848.2532592","DOI":"10.1145\/2522848.2532592"},{"issue":"2","key":"19_CR13","first-page":"157","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Y. Bengio, P. Simard, P. Frasconi, Learning long-term dependencies with gradient descent is difficult. TNN 5(2), 157\u2013166 (1994)","journal-title":"TNN"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"H.\u00a0Bilen, B.\u00a0Fernando, E.\u00a0Gavves, A.\u00a0Vedaldi, S.\u00a0Gould, Dynamic image networks for action recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 3034\u20133042","DOI":"10.1109\/CVPR.2016.331"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"N.C. Camgoz, S.\u00a0Hadfield, O.\u00a0Koller, R.\u00a0Bowden, Using convolutional 3d neural networks for user-independent continuous gesture recognition, in Proceedings IEEE International Conference of Pattern Recognition (International Conference on Pattern Recognition), ChaLearn Workshop, 2016","DOI":"10.1109\/ICPR.2016.7899606"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"X.\u00a0Chai, Z.\u00a0Liu, F.\u00a0Yin, Z.\u00a0Liu, X.\u00a0Chen, Two streams recurrent neural networks for large-scale continuous gesture recognition, in Proceedings of International Conference on Pattern RecognitionW, 2016","DOI":"10.1109\/ICPR.2016.7899603"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"R.\u00a0Chaudhry, F.\u00a0Ofli, G.\u00a0Kurillo, R.\u00a0Bajcsy, R.\u00a0Vidal, Bio-inspired dynamic 3d discriminative skeletal features for human action recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2013, pp. 471\u2013478","DOI":"10.1109\/CVPRW.2013.153"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"R.\u00a0Chavarriaga, H.\u00a0Sagha, J.\u00a0del R.\u00a0Milln, Ensemble creation and reconfiguration for activity recognition: an information theoretic approach, in SMC, 2011, pp. 2761\u20132766. ISBN 978-1-4577-0652-3, http:\/\/dblp.uni-trier.de\/db\/conf\/smc\/smc2011.html#ChavarriagaSM11","DOI":"10.1109\/ICSMC.2011.6084090"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"C.\u00a0Chen, B.\u00a0Zhang, Z.\u00a0Hou, J.\u00a0Jiang, M.\u00a0Liu, Y.\u00a0Yang, Action recognition from depth sequences using weighted fusion of 2d and 3d auto-correlation of gradients features, in Multimedia Tools and Applications, 2016, pp. 1\u201319","DOI":"10.1007\/s11042-016-3284-7"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"W.\u00a0Chen, J.J. Corso, Action detection by implicit intentional motion clustering, in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 3298\u20133306","DOI":"10.1109\/ICCV.2015.377"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"G.\u00a0Ch\u00e9ron, I.\u00a0Laptev, C.\u00a0Schmid, P-cnn: pose-based cnn features for action recognition, in Proceedings of the IEEE International Conference on Computer Vision, pp. 3218\u20133226, 2015","DOI":"10.1109\/ICCV.2015.368"},{"key":"19_CR22","volume-title":"Torch: a modular machine learning software library","author":"R Collobert","year":"2002","unstructured":"R. Collobert, S. Bengio, J. Marithoz, Torch: a modular machine learning software library (Technical Report, IDIAP, 2002)"},{"key":"19_CR23","doi-asserted-by":"publisher","unstructured":"Z.\u00a0Deng, M.\u00a0Zhai, L.\u00a0Chen, Y.\u00a0Liu, S.\u00a0Muralidharan, M.J. Roshtkhari, G.\u00a0Mori, Deep structured models for group activity recognition, in Proceedings of the British Machine Vision Conference (BMVC) ed. by M.W.J. Xianghua\u00a0Xie, G.K.L. Tam (BMVA Press, Guildford, 2015), pp. 179.1\u2013179.12. ISBN 1-901725-53-7. doi: 10.5244\/C.29.179","DOI":"10.5244\/C.29.179"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Deng, A.\u00a0Vahdat, H.\u00a0Hu, G.\u00a0Mori, Structure inference machines: recurrent neural networks for analyzing relations in group activity recognition, in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.516"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"A.\u00a0Diba, A.\u00a0Mohammad\u00a0Pazandeh, H.\u00a0Pirsiavash, L.\u00a0Van\u00a0Gool, Deepcamp: deep convolutional action and attribute mid-level patterns, in IEEE CVPR, 2016","DOI":"10.1109\/CVPR.2016.387"},{"key":"19_CR26","doi-asserted-by":"publisher","unstructured":"Y.\u00a0Du, W.\u00a0Wang, L.\u00a0Wang, Hierarchical recurrent neural network for skeleton based action recognition, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015, pp. 1110\u20131118. doi: 10.1109\/CVPR.2015.7298714","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"19_CR27","unstructured":"J.\u00a0Duan, S.\u00a0Zhou, J.\u00a0Wan, X.\u00a0Guo, S.Z. Li, Multi-modality fusion based on consensus-voting and 3d convolution for isolated gesture recognition, 2016, arXiv:1611.06689"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"I.C. Duta, B.\u00a0Ionescu, K.\u00a0Aizawa, N.\u00a0Sebe, Spatio-temporal vlad encoding for human action recognition in videos, in International Conference on Multimedia Modeling (Springer, New York, 2017), pp. 365\u2013378","DOI":"10.1007\/978-3-319-51811-4_30"},{"key":"19_CR29","unstructured":"T.\u00a0Eleni, Gesture recognition with a convolutional long short term memory recurrent neural network, in ESANN, 2015, https:\/\/books.google.cl\/books?id=E8qMjwEACAAJ"},{"issue":"2","key":"19_CR30","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","volume":"14","author":"JL Elman","year":"1990","unstructured":"J.L. Elman, Finding structure in time. Cognitive Sci. 14(2), 179\u2013211 (1990)","journal-title":"Finding structure in time. Cognitive Sci."},{"key":"19_CR31","doi-asserted-by":"publisher","unstructured":"H.J. Escalante, C.A. H\u00e9rnadez, L.E. Sucar, M.\u00a0Montes. Late fusion of heterogeneous methods for multimedia image retrieval, in Proceedings of the 1st ACM International Conference on Multimedia Information Retrieval, MIR\u201908 (ACM, New York, 2008), pp. 172\u2013179. ISBN 978-1-60558-312-9. doi: 10.1145\/1460096.1460125","DOI":"10.1145\/1460096.1460125"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"H.J. Escalante, I.\u00a0Guyon, V.\u00a0Athitsos, P.\u00a0Jangyodsuk, J.\u00a0Wan, Principal motion components for gesture recognition using a single example, in PAA, 2015","DOI":"10.1007\/s10044-015-0481-3"},{"key":"19_CR33","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.patrec.2016.01.013","volume":"73","author":"HJ Escalante","year":"2016","unstructured":"H.J. Escalante, E.F. Morales, L.E. Sucar, A na\u00efve bayes baseline for early gesture recognition. PRL 73, 91\u201399 (2016a)","journal-title":"PRL"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"H.J. Escalante, V.\u00a0Ponce, J.\u00a0Wan, M.\u00a0Riegler, A.\u00a0Clapes, S.\u00a0Escalera, I.\u00a0Guyon, X.\u00a0Baro, P.\u00a0Halvorsen, H.\u00a0M\u00fcller, M.\u00a0Larson, Chalearn joint contest on multimedia challenges beyond visual analysis: an overview, in Proceedings of International Conference on Pattern Recognition, 2016b","DOI":"10.1109\/ICPR.2016.7899609"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"V.\u00a0Escorcia, F.C. Heilbron, J.C. Niebles, B.\u00a0Ghanem, DAPs: deep action proposals for action understanding, in European Conference on Computer Vision, 2016","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"C.\u00a0Feichtenhofer, A.\u00a0Pinz, R.\u00a0Wildes, Spatiotemporal residual networks for video action recognition, in Advances in Neural Information Processing Systems, 2016a, pp. 3468\u20133476","DOI":"10.1109\/CVPR.2017.787"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"C.\u00a0Feichtenhofer, A.\u00a0Pinz, A.\u00a0Zisserman, Convolutional two-stream network fusion for video action recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016b, pp. 1933\u20131941","DOI":"10.1109\/CVPR.2016.213"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"B.\u00a0Fernando, E.\u00a0Gavves, J.\u00a0Oramas, A.\u00a0Ghodrati, T.\u00a0Tuytelaars, Rank pooling for action recognition, in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016","DOI":"10.1109\/TPAMI.2016.2558148"},{"key":"19_CR39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cviu.2015.02.008","volume":"134","author":"D Fortun","year":"2015","unstructured":"D. Fortun, P. Bouthemy, C. Kervrann, Optical flow modeling and computation: a survey. Comput. Vis. Image Underst. 134, 1\u201321 (2015)","journal-title":"Comput. Vis. Image Underst."},{"key":"19_CR40","first-page":"115","volume":"3","author":"FA Gers","year":"2002","unstructured":"F.A. Gers, N.N. Schraudolph, J. Schmidhuber, Learning precise timing with lstm recurrent networks. JMLR 3, 115\u2013143 (2002)","journal-title":"JMLR"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"G.\u00a0Gkioxari, J.\u00a0Malik, Finding action tubes, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 759\u2013768","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"A.\u00a0Grushin, D.D. Monner, J.A. Reggia, A.\u00a0Mishra, Robust human action recognition via long short-term memory, in The 2013 International Joint Conference on, Neural Networks (IJCNN), IEEE, 2013, pp. 1\u20138","DOI":"10.1109\/IJCNN.2013.6706797"},{"key":"19_CR43","doi-asserted-by":"publisher","unstructured":"F.\u00a0Gu, M.\u00a0Sridhar, A.\u00a0Cohn, D.\u00a0Hogg, F.\u00a0Flrez-Revuelta, D.\u00a0Monekosso, P.\u00a0Remagnino, Weakly supervised activity analysis with spatio-temporal localisation, Neurocomputing, 2016. ISSN 0925-2312. doi: 10.1016\/j.neucom.2016.08.032 , http:\/\/www.sciencedirect.com\/science\/article\/","DOI":"10.1016\/j.neucom.2016.08.032"},{"key":"19_CR44","unstructured":"S.\u00a0Han, H.\u00a0Mao, W.\u00a0Dally, Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding, in Proceedings of International Conference on Learning Representations, 2016"},{"key":"19_CR45","doi-asserted-by":"crossref","unstructured":"K.\u00a0He, X.\u00a0Zhang, S.\u00a0Ren, J.\u00a0Sun, Deep residual learning for image recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016a, pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"19_CR46","doi-asserted-by":"crossref","unstructured":"Y.\u00a0He, S.\u00a0Shirakabe, Y.\u00a0Satoh, H.\u00a0Kataoka, Human action recognition without human, in Proceedings of European Conference on Computer Vision 2016 Workshops (Springer, New York, 2016b), pp. 11\u201317","DOI":"10.1007\/978-3-319-49409-8_2"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"F.C. Heilbron, V.\u00a0Escorcia, B.\u00a0Ghanem, J.C. Niebles, Activitynet: a large-e video benchmark for human activity understanding, in CVPR, 2015, pp. 961\u2013970","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"19_CR48","first-page":"91","volume-title":"Untersuchungen zu dynamischen neuronalen netzen","author":"S Hochreiter","year":"1991","unstructured":"S. Hochreiter, Untersuchungen zu dynamischen neuronalen netzen (Technische Universit\u00e4t M\u00fcnchen, Diploma, 1991), p. 91"},{"issue":"8","key":"19_CR49","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"S. Hochreiter, J. Schmidhuber, Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"J.\u00a0Huang, W.\u00a0Zhou, H.\u00a0Li, W.\u00a0Li, Sign language recognition using 3d convolutional neural networks, in ICME, 2015, pp. 1\u20136","DOI":"10.1109\/ICME.2015.7177428"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"M.S. Ibrahim, S.\u00a0Muralidharan, Z.\u00a0Deng, A.\u00a0Vahdat, G.\u00a0Mori, A hierarchical deep temporal model for group activity recognition, in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.217"},{"key":"19_CR52","unstructured":"A.\u00a0Jain, J.\u00a0Tompson, M.\u00a0Andriluka, G.W. Taylor, C.\u00a0Bregler, Learning human pose estimation features with convolutional networks, in International Conference on Learning Representations, Cornell University, 2014a, pp. 1\u201314"},{"key":"19_CR53","doi-asserted-by":"crossref","unstructured":"A.\u00a0Jain, J.\u00a0Tompson, Y.\u00a0LeCun, C.\u00a0Bregler, MoDeep: a deep learning framework using motion features for human pose estimation, vol. 9004, 2015a, pp. 302\u2013315","DOI":"10.1007\/978-3-319-16808-1_21"},{"key":"19_CR54","unstructured":"M. Jain, J. van Gemert, C.G.M. Snoek, University of Amsterdam at thumos challenge, in ECCV THUMOS Challenge 2014 (Z\u00fcrich, Switzerland, September, 2014), 2014b"},{"key":"19_CR55","doi-asserted-by":"crossref","unstructured":"M.\u00a0Jain, J.C. van Gemert, T.\u00a0Mensink, C.G.M. Snoek. Objects2action: classifying and localizing actions without any video example, in IEEE ICCV, 2015b, arXiv.org\/abs\/1510.06939","DOI":"10.1109\/ICCV.2015.521"},{"key":"19_CR56","doi-asserted-by":"crossref","unstructured":"M.\u00a0Jain, J.C. van Gemert, C.G. Snoek, What do 15,000 object categories tell us about classifying and localizing actions? in CVPR, 2015c, pp. 46\u201355","DOI":"10.1109\/CVPR.2015.7298599"},{"key":"19_CR57","unstructured":"S.\u00a0Ji, W.\u00a0Xu, M.\u00a0Yang, K.\u00a0Yu. 3d convolutional neural networks for human action recognition, in Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010, pp. 495\u2013502"},{"key":"19_CR58","doi-asserted-by":"publisher","unstructured":"S.\u00a0Ji, W.\u00a0Xu, M.\u00a0Yang, K.\u00a0Yu. 3d convolutional neural networks for human action recognition. IEEE TPAMI, vol. 35(1), 2013, pp. 221\u2013231. ISSN 0162-8828. doi: 10.1109\/TPAMI.2012.59","DOI":"10.1109\/TPAMI.2012.59"},{"key":"19_CR59","first-page":"675","volume-title":"Caffe: convolutional architecture for fast feature embedding, in ACM MM","author":"Y Jia","year":"2014","unstructured":"Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, T. Darrell, Caffe: convolutional architecture for fast feature embedding, in ACM MM (ACM, New York, 2014), pp. 675\u2013678"},{"key":"19_CR60","unstructured":"Y.-G. Jiang, J.\u00a0Liu, A.\u00a0Roshan\u00a0Zamir, I.\u00a0Laptev, M.\u00a0Piccardi, M.\u00a0Shah, R.\u00a0Sukthankar, THUMOS challenge: action recognition with a large number of classes. ICCV13-Action-Workshop, 2013"},{"key":"19_CR61","doi-asserted-by":"crossref","unstructured":"V.\u00a0John, A.\u00a0Boyali, S.\u00a0Mita, M.\u00a0Imanishi, N.\u00a0Sanma. Deep learning-based fast hand gesture recognition using representative frames, in 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), IEEE, 2016, pp. 1\u20138","DOI":"10.1109\/DICTA.2016.7797030"},{"key":"19_CR62","doi-asserted-by":"crossref","unstructured":"J.\u00a0Joo, W.\u00a0Li, F.F. Steen, S.-C. Zhu. Visual persuasion: Inferring communicative intents of images, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 216\u2013223","DOI":"10.1109\/CVPR.2014.35"},{"key":"19_CR63","doi-asserted-by":"crossref","unstructured":"B.\u00a0Kang, S.\u00a0Tripathi, T.Q. Nguyen, Real-time sign language fingerspelling recognition using convolutional neural networks from depth map, in ACPR, 2015, arXiv:abs\/1509.03001","DOI":"10.1109\/ACPR.2015.7486481"},{"key":"19_CR64","doi-asserted-by":"crossref","unstructured":"S.\u00a0Karaman, L.\u00a0Seidenari, A.D. Bagdanov, A.D. Bimbo, L1-regularized logistic regression stacking and transductive crf smoothing for action recognition in video, in Results of the THUMOS 2013 Action Recognition Challenge with a Large Number of Classes, 2013","DOI":"10.5244\/C.28.112"},{"key":"19_CR65","doi-asserted-by":"crossref","unstructured":"A.\u00a0Karpathy, G.\u00a0Toderici, S.\u00a0Shetty, T.\u00a0Leung, R.\u00a0Sukthankar, and L.\u00a0Fei-Fei. Large-scale video classification with convolutional neural networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 1725\u20131732","DOI":"10.1109\/CVPR.2014.223"},{"key":"19_CR66","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.cviu.2016.10.004","volume":"154","author":"T Kerola","year":"2017","unstructured":"T. Kerola, N. Inoue, K. Shinoda, Cross-view human action recognition from depth maps using spectral graph sequences. Comput. Vis. Image Underst. 154, 108\u2013126 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"19_CR67","doi-asserted-by":"crossref","unstructured":"O.\u00a0Koller, H.\u00a0Ney, R.\u00a0Bowden, Deep hand: how to train a cnn on 1 million hand images when your data is continuous and weakly labelled, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 3793\u20133802","DOI":"10.1109\/CVPR.2016.412"},{"key":"19_CR68","unstructured":"J.\u00a0Konecny, M.\u00a0Hagara, One-shot-learning gesture recognition using hog-hof features, in JMLR, vol. 15, 2014, pp. 2513\u20132532, http:\/\/jmlr.org\/papers\/v15\/konecny14a.html"},{"key":"19_CR69","unstructured":"A.\u00a0Krizhevsky, I.\u00a0Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems, 2012, pp. 1097\u20131105"},{"key":"19_CR70","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Kuniyoshi, H.\u00a0Inoue, M.\u00a0Inaba, Design and implementation of a system that generates assembly programs from visual recognition of human action sequences, in IEEE International Workshop on Intelligent Robots and Systems\u2019 90.\u2019Towards a New Frontier of Applications\u2019, Proceedings, IROS\u201990, IEEE, 1990, pp. 567\u2013574","DOI":"10.1109\/IROS.1990.262444"},{"key":"19_CR71","doi-asserted-by":"crossref","unstructured":"G.\u00a0Lev, G.\u00a0Sadeh, B.\u00a0Klein, L.\u00a0Wolf, Rnn fisher vectors for action recognition and image annotation, in European Conference on Computer Vision (Springer, New York, 2016), pp. 833\u2013850","DOI":"10.1007\/978-3-319-46466-4_50"},{"key":"19_CR72","doi-asserted-by":"publisher","unstructured":"S.\u00a0Li, Z.-Q. Liu, A.B. Chan, Heterogeneous multi-task learning for human pose estimation with deep convolutional neural network. IJCV, vol. 113(1), May 2015a, pp. 19\u201336. ISSN 0920-5691. doi: 10.1007\/s11263-014-0767-8","DOI":"10.1007\/s11263-014-0767-8"},{"key":"19_CR73","doi-asserted-by":"crossref","unstructured":"S.\u00a0Li, W.\u00a0Zhang, A.B. Chan, Maximum-margin structured learning with deep networks for 3d human pose estimation, in ICCV, 2015b, pp. 2848\u20132856","DOI":"10.1109\/ICCV.2015.326"},{"key":"19_CR74","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Li, W.\u00a0Li, V.\u00a0Mahadevan, N.\u00a0Vasconcelos, Vlad3: encoding dynamics of deep features for action recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016a, pp. 1951\u20131960","DOI":"10.1109\/CVPR.2016.215"},{"key":"19_CR75","unstructured":"Y.\u00a0Li, Q.\u00a0Miao, K.\u00a0Tian, Y.\u00a0Fan, X.\u00a0Xu, R.\u00a0Li, J.\u00a0Song, Large-scale gesture recognition with a fusion of rgb-d data based on c3d model, in Proceedings of International Conference on Pattern RecognitionW, 2016b"},{"key":"19_CR76","doi-asserted-by":"crossref","unstructured":"C.\u00a0Liang, Y.\u00a0Song, Y.\u00a0Zhang, Hand gesture recognition using view projection from point cloud, in 2016 IEEE International Conference on Image Processing (ICIP), IEEE, 2016, pp. 4413\u20134417","DOI":"10.1109\/ICIP.2016.7533194"},{"key":"19_CR77","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Liang, G.\u00a0Zhang, J.X. Huang, Q.V. Hu, Deep learning for healthcare decision making with emrs, in 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, 2014, pp. 556\u2013559","DOI":"10.1109\/BIBM.2014.6999219"},{"key":"19_CR78","doi-asserted-by":"crossref","unstructured":"H.-I. Lin, M.-H. Hsu, W.-K. Chen, Human hand gesture recognition using a convolution neural network, in CASE, 2015, pp. 1038\u20131043","DOI":"10.1109\/CoASE.2014.6899454"},{"issue":"1","key":"19_CR79","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1109\/TPAMI.2016.2537337","volume":"39","author":"A-A Liu","year":"2017","unstructured":"A.-A. Liu, Y.-T. Su, W.-Z. Nie, M. Kankanhalli, Hierarchical clustering multi-task learning for joint human action grouping and recognition. TPAMI 39(1), 102\u2013114 (2017)","journal-title":"TPAMI"},{"key":"19_CR80","doi-asserted-by":"crossref","unstructured":"J.\u00a0Liu, A.\u00a0Shahroudy, D.\u00a0Xu, G.\u00a0Wang, Spatio-temporal lstm with trust gates for 3d human action recognition, in European Conference on Computer Vision (Springer, New York, 2016a), pp. 816\u2013833","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"19_CR81","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.imavis.2016.04.004","volume":"55","author":"Z Liu","year":"2016","unstructured":"Z. Liu, C. Zhang, Y. Tian, 3d-based deep convolutional neural network for action recognition with depth sequences. Image Vis. Comput. 55, 93\u2013100 (2016b)","journal-title":"Image Vis. Comput."},{"key":"19_CR82","doi-asserted-by":"crossref","unstructured":"J.\u00a0Luo, W.\u00a0Wang, H.\u00a0Qi, Group sparsity and geometry constrained dictionary learning for action recognition from depth maps, in Proceedings of the IEEE International Conference on Computer Vision, 2013, pp. 1809\u20131816","DOI":"10.1109\/ICCV.2013.227"},{"key":"19_CR83","doi-asserted-by":"crossref","unstructured":"B.\u00a0Mahasseni, S.\u00a0Todorovic, Regularizing long short term memory with 3d human-skeleton sequences for action recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 3054\u20133062","DOI":"10.1109\/CVPR.2016.333"},{"key":"19_CR84","unstructured":"E.\u00a0Mansimov, N.\u00a0Srivastava, R.\u00a0Salakhutdinov, Initialization strategies of spatio-temporal convolutional neural networks, 2015, arXiv:1503.07274"},{"key":"19_CR85","unstructured":"R.\u00a0Marks, System and method for providing a real-time three-dimensional interactive environment, Dec.\u00a06 2011. US Patent 8,072,470"},{"key":"19_CR86","doi-asserted-by":"crossref","unstructured":"P.\u00a0Mettes, J.C. van Gemert, C.G. Snoek, Spot on: action localization from pointly-supervised proposals, in European Conference on Computer Vision (Springer, New York, 2016), pp. 437\u2013453","DOI":"10.1007\/978-3-319-46454-1_27"},{"issue":"7540","key":"19_CR87","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"V. Mnih, K. Kavukcuoglu, D. Silver, A.A. Rusu, J. Veness, M.G. Bellemare, A. Graves, M. Riedmiller, A.K. Fidjeland, G. Ostrovski et al., Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"19_CR88","doi-asserted-by":"publisher","unstructured":"P.\u00a0Molchanov, S.\u00a0Gupta, K.\u00a0Kim, J.\u00a0Kautz, Hand gesture recognition with 3d convolutional neural networks, in CVPRW, June 2015, pp. 1\u20137. doi: 10.1109\/CVPRW.2015.7301342","DOI":"10.1109\/CVPRW.2015.7301342"},{"key":"19_CR89","doi-asserted-by":"crossref","unstructured":"P.\u00a0Molchanov, X.\u00a0Yang, S.\u00a0Gupta, K.\u00a0Kim, S.\u00a0Tyree, J.\u00a0Kautz, Online detection and classification of dynamic hand gestures with recurrent 3d convolutional neural network, in CVPR, 2016","DOI":"10.1109\/CVPR.2016.456"},{"key":"19_CR90","unstructured":"A.\u00a0Montes, A.\u00a0Salvador, X.\u00a0Giro-i Nieto, Temporal activity detection in untrimmed videos with recurrent neural networks, 2016, arXiv:1608.08128"},{"key":"19_CR91","doi-asserted-by":"publisher","unstructured":"H.\u00a0Mousavi\u00a0Hondori, M.\u00a0Khademi, A review on technical and clinical impact of microsoft kinect on physical therapy and rehabilitation. J. Med. Eng. (2014). doi: 10.1155\/2014\/846514","DOI":"10.1155\/2014\/846514"},{"key":"19_CR92","doi-asserted-by":"crossref","unstructured":"K.\u00a0Nasrollahi, S.\u00a0Escalera, P.\u00a0Rasti, G.\u00a0Anbarjafari, X.\u00a0Bar, H.J. Escalante, T.B. Moeslund, Deep learning based super-resolution for improved action recognition, in IPTA, 2015, pp. 67\u201372. ISBN 978-1-4799-8637-8, http:\/\/dblp.uni-trier.de\/db\/conf\/ipta\/ipta2015.html#NasrollahiERABE15","DOI":"10.1109\/IPTA.2015.7367098"},{"key":"19_CR93","doi-asserted-by":"crossref","unstructured":"N.\u00a0Neverova, C.\u00a0Wolf, G.\u00a0Paci, G.\u00a0Sommavilla, G.W. Taylor, F.\u00a0Nebout, A multi-scale approach to gesture detection and recognition, in ICCVW, 2013, pp. 484\u2013491, http:\/\/liris.cnrs.fr\/publis\/?id=6330","DOI":"10.1109\/ICCVW.2013.69"},{"key":"19_CR94","first-page":"474","volume":"8925","author":"N Neverova","year":"2014","unstructured":"N. Neverova, C. Wolf, G.W. Taylor, F. Nebout, Multi-scale deep learning for gesture detection and localization. ECCVW. LNCS 8925, 474\u2013490 (2014)","journal-title":"ECCVW. LNCS"},{"key":"19_CR95","doi-asserted-by":"publisher","unstructured":"N.\u00a0Neverova, C.\u00a0Wolf, G.W. Taylor, F.\u00a0Nebout, Hand segmentation with structured convolutional learning, in ACCV. LNCS, vol. 9005, 2015a, pp. 687\u2013702. ISBN 978-3-319-16811-1. doi: 10.1007\/978-3-319-16811-1_45","DOI":"10.1007\/978-3-319-16811-1_45"},{"key":"19_CR96","doi-asserted-by":"crossref","unstructured":"N.\u00a0Neverova, C.\u00a0Wolf, G.W. Taylor, F.\u00a0Nebout, Moddrop: adaptive multi-modal gesture recognition, in IEEE TPAMI, 2015b","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"19_CR97","unstructured":"J.Y.-H. Ng, J.\u00a0Choi, J.\u00a0Neumann, L.S. Davis, Actionflownet: learning motion representation for action recognition, 2016, arXiv:1612.03052"},{"key":"19_CR98","doi-asserted-by":"publisher","unstructured":"B.\u00a0Ni, Y.\u00a0Pei, Z.\u00a0Liang, L.\u00a0Lin, P.\u00a0Moulin, Integrating multi-stage depth-induced contextual information for human action recognition and localization, in FG, April 2013, pp 1\u20138. doi: 10.1109\/FG.2013.6553756","DOI":"10.1109\/FG.2013.6553756"},{"key":"19_CR99","doi-asserted-by":"crossref","unstructured":"B.\u00a0Ni, X.\u00a0Yang, S.\u00a0Gao, Progressively parsing interactional objects for fine grained action detection, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1020\u20131028","DOI":"10.1109\/CVPR.2016.116"},{"key":"19_CR100","doi-asserted-by":"crossref","unstructured":"N.\u00a0Nishida, H.\u00a0Nakayama, Multimodal gesture recognition using multi-stream recurrent neural network, in PSIVT, 2016, pp. 682\u2013694","DOI":"10.1007\/978-3-319-29451-3_54"},{"key":"19_CR101","doi-asserted-by":"publisher","unstructured":"S.\u00a0Oh, A large-scale benchmark dataset for event recognition in surveillance video, in CVPR, 2011, pp. 3153\u20133160. ISBN 978-1-4577-0394-2. doi: 10.1109\/CVPR.2011.5995586","DOI":"10.1109\/CVPR.2011.5995586"},{"key":"19_CR102","doi-asserted-by":"publisher","unstructured":"E.\u00a0Ohn-Bar, M.M. Trivedi, Hand gesture recognition in real time for automotive interfaces: a multimodal vision-based approach and evaluations, in IEEE-ITS, vol. 15(6), Dec 2014, pp. 2368\u20132377. ISSN 1524-9050. doi: 10.1109\/TITS.2014.2337331","DOI":"10.1109\/TITS.2014.2337331"},{"issue":"1","key":"19_CR103","doi-asserted-by":"crossref","first-page":"115","DOI":"10.3390\/s16010115","volume":"16","author":"FJ Ord\u00f3\u00f1ez","year":"2016","unstructured":"F.J. Ord\u00f3\u00f1ez, D. Roggen, Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1), 115 (2016)","journal-title":"Sensors"},{"key":"19_CR104","doi-asserted-by":"crossref","unstructured":"W.\u00a0Ouyang, X.\u00a0Chu, X.\u00a0Wang, Multi-source deep learning for human pose estimation, in CVPR, 2014, pp. 2337\u20132344","DOI":"10.1109\/CVPR.2014.299"},{"key":"19_CR105","doi-asserted-by":"crossref","unstructured":"O.K. Oyedotun, A.\u00a0Khashman, Deep learning in vision-based static hand gesture recognition, in Neural Computing and Applications, 2016, pp. 1\u201311","DOI":"10.1007\/s00521-016-2294-8"},{"key":"19_CR106","doi-asserted-by":"crossref","unstructured":"E.\u00a0Park, X.\u00a0Han, T.L. Berg, A.C. Berg, Combining multiple sources of knowledge in deep cnns for action recognition, in 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, 2016, pp. 1\u20138","DOI":"10.1109\/WACV.2016.7477589"},{"key":"19_CR107","unstructured":"X.\u00a0Peng, C.\u00a0Schmid, Encoding feature maps of cnns for action recognition, in CVPR, THUMOS Challenge 2015 Workshop, 2015"},{"key":"19_CR108","doi-asserted-by":"crossref","unstructured":"X.\u00a0Peng, C.\u00a0Schmid, Multi-region two-stream r-cnn for action detection, in European Conference on Computer Vision (Springer, New York, 2016), pp. 744\u2013759","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"19_CR109","unstructured":"X.\u00a0Peng, L.\u00a0Wang, Z.\u00a0Cai, Y.\u00a0Qiao, Q.\u00a0Peng, Hybrid super vector with improved dense trajectories for action recognition, in ICCV Workshops, vol. 13, 2013"},{"key":"19_CR110","doi-asserted-by":"crossref","unstructured":"X.\u00a0Peng, C.\u00a0Zou, Y.\u00a0Qiao, Q.\u00a0Peng, Action recognition with stacked fisher vectors, in European Conference on Computer Vision (Springer, New York, 2014), pp. 581\u2013595","DOI":"10.1007\/978-3-319-10602-1_38"},{"key":"19_CR111","doi-asserted-by":"publisher","unstructured":"X.\u00a0Peng, L.\u00a0Wang, Z.\u00a0Cai, Y.\u00a0Qiao, Action and Gesture Temporal Spotting with Super Vector Representation, 2015, pp. 518\u2013527. ISBN 978-3-319-16178-5. doi: 10.1007\/978-3-319-16178-5_36","DOI":"10.1007\/978-3-319-16178-5_36"},{"key":"19_CR112","doi-asserted-by":"publisher","unstructured":"L.\u00a0Pigou, S.\u00a0Dieleman, P.-J. Kindermans, B.\u00a0Schrauwen, Sign language recognition using convolutional neural networks, in European Conference on Computer Vision\u201914, 2015a, pp. 572\u2013578. ISBN 978-3-319-16178-5. doi: 10.1007\/978-3-319-16178-5_40","DOI":"10.1007\/978-3-319-16178-5_40"},{"key":"19_CR113","unstructured":"L.\u00a0Pigou, A.V.D. Oord, S.\u00a0Dieleman, M.V. Herreweghe, J.\u00a0Dambre, Beyond temporal pooling: recurrence and temporal convolutions for gesture recognition in video. CoRR, 2015b, arXiv.org\/abs\/1506.01911"},{"key":"19_CR114","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Poleg, A.\u00a0Ephrat, S.\u00a0Peleg, C.\u00a0Arora, Compact cnn for indexing egocentric videos, in 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, 2016, pp. 1\u20139","DOI":"10.1109\/WACV.2016.7477708"},{"key":"19_CR115","unstructured":"Z. Qiu, Q. Li, T. Yao, T. Mei, Y. Rui, Msr asia msm at thumos challenge 2015, in CVPR Workshop, vol. 8 (2015)"},{"key":"19_CR116","unstructured":"A.\u00a0Radford, L.\u00a0Metz, S.\u00a0Chintala, Unsupervised representation learning with deep convolutional generative adversarial networks, in Proceedings of International Conference on Learning Representations, 2016"},{"key":"19_CR117","doi-asserted-by":"crossref","unstructured":"H.\u00a0Rahmani, A.\u00a0Mian, 3d action recognition from novel viewpoints, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1506\u20131515","DOI":"10.1109\/CVPR.2016.167"},{"key":"19_CR118","unstructured":"H.\u00a0Rahmani, A.\u00a0Mian, and M.\u00a0Shah. Learning a deep model for human action recognition from novel viewpoints, arXiv preprint arXiv:1602.00828"},{"key":"19_CR119","unstructured":"S.\u00a0Ren, K.\u00a0He, R.\u00a0Girshick, J.\u00a0Sun, Faster r-cnn: towards real-time object detection with region proposal networks, in Advances in neural information processing systems, 2015, pp. 91\u201399"},{"key":"19_CR120","doi-asserted-by":"crossref","unstructured":"N.\u00a0Rhinehart, K.M. Kitani, Learning action maps of large environments via first-person vision, in Proceedings of European Conference on Computer Vision, 2016","DOI":"10.1109\/CVPR.2016.69"},{"key":"19_CR121","doi-asserted-by":"crossref","unstructured":"A.\u00a0Richard, J.\u00a0Gall, Temporal action detection using a statistical language model, in CVPR, 2016","DOI":"10.1109\/CVPR.2016.341"},{"key":"19_CR122","doi-asserted-by":"publisher","unstructured":"H.\u00a0Sagha, J.\u00a0del R.\u00a0Milln, R.\u00a0Chavarriaga, Detecting anomalies to improve classification performance in opportunistic sensor networks, in PERCOM Workshops, March 2011a, pp. 154\u2013159. doi: 10.1109\/PERCOMW.2011.5766860","DOI":"10.1109\/PERCOMW.2011.5766860"},{"key":"19_CR123","doi-asserted-by":"publisher","unstructured":"H.\u00a0Sagha, S.T. Digumarti, J.\u00a0del R.\u00a0Mill\u00e1n, R.\u00a0Chavarriaga, A.\u00a0Calatroni, D.\u00a0Roggen, G.\u00a0Tr\u00f6ster, Benchmarking classification techniques using the opportunity human activity dataset, in IEEE SMC, Oct 2011b, pp. 36 \u201340. doi: 10.1109\/ICSMC.2011.6083628","DOI":"10.1109\/ICSMC.2011.6083628"},{"key":"19_CR124","doi-asserted-by":"crossref","unstructured":"S.\u00a0Saha, G.\u00a0Singh, M.\u00a0Sapienza, P.H. Torr, F.\u00a0Cuzzolin, Deep learning for detecting multiple space-time action tubes in videos, 2016, arXiv:1608.01529","DOI":"10.5244\/C.30.58"},{"key":"19_CR125","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-39608-3","volume-title":"Computer vision techniques for the diagnosis of skin cancer","author":"J Scharcanski","year":"2014","unstructured":"J. Scharcanski, M.E. Celebi, Computer vision techniques for the diagnosis of skin cancer (Springer, New York, 2014)"},{"key":"19_CR126","doi-asserted-by":"crossref","unstructured":"A.\u00a0Shahroudy, J.\u00a0Liu, T.-T. Ng, G.\u00a0Wang, NTU RGB+ D: a large scale dataset for 3d human activity analysis, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016a, pp. 1010\u20131019","DOI":"10.1109\/CVPR.2016.115"},{"key":"19_CR127","unstructured":"A.\u00a0Shahroudy, T.-T. Ng, Y.\u00a0Gong, G.\u00a0Wang, Deep multimodal feature analysis for action recognition in RGB+ D videos, 2016b, arXiv:1603.07120"},{"key":"19_CR128","doi-asserted-by":"crossref","unstructured":"L.\u00a0Shao, L.\u00a0Liu, M.\u00a0Yu, Kernelized multiview projection for robust action recognition. Int. J. Comput. Vis. 118(2), 115\u2013129, June 2016, http:\/\/nrl.northumbria.ac.uk\/24276\/","DOI":"10.1007\/s11263-015-0861-6"},{"key":"19_CR129","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Shou, D.\u00a0Wang, S.-F. Chang, Temporal action localization in untrimmed videos via multi-stage CNNS, in CVPR, 2016a","DOI":"10.1109\/CVPR.2016.119"},{"key":"19_CR130","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Shou, D.\u00a0Wang, S.-F. Chang, Temporal action localization in untrimmed videos via multi-stage CNNS. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016b, pp. 1049\u20131058","DOI":"10.1109\/CVPR.2016.119"},{"key":"19_CR131","doi-asserted-by":"publisher","unstructured":"Z.\u00a0Shu, K.\u00a0Yun, D.\u00a0Samaras, Action Detection with Improved Dense Trajectories and Sliding Window, Cham, 2015, pp. 541\u2013551. ISBN 978-3-319-16178-5. doi: 10.1007\/978-3-319-16178-5_38","DOI":"10.1007\/978-3-319-16178-5_38"},{"key":"19_CR132","doi-asserted-by":"crossref","unstructured":"K.\u00a0Simonyan, A.\u00a0Zisserman, Two-stream convolutional networks for action recognition in videos, in NIPS, 2014, pp. 568\u2013576","DOI":"10.1109\/CVPR.2016.216"},{"key":"19_CR133","doi-asserted-by":"crossref","unstructured":"B.\u00a0Singh, T.K. Marks, M.\u00a0Jones, O.\u00a0Tuzel, M.\u00a0Shao, A multi-stream bi-directional recurrent neural network for fine-grained action detection, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016a, pp. 1961\u20131970","DOI":"10.1109\/CVPR.2016.287"},{"key":"19_CR134","doi-asserted-by":"crossref","unstructured":"S.\u00a0Singh, C.\u00a0Arora, C.\u00a0Jawahar, First person action recognition using deep learned descriptors, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016b, pp. 2620\u20132628","DOI":"10.1109\/CVPR.2016.287"},{"key":"19_CR135","doi-asserted-by":"crossref","unstructured":"K.\u00a0Soomro, H.\u00a0Idrees, M.\u00a0Shah, Action localization in videos through context walk, in ICCV, 2015","DOI":"10.1109\/ICCV.2015.375"},{"key":"19_CR136","doi-asserted-by":"crossref","unstructured":"W.\u00a0Sultani, M.\u00a0Shah, Automatic action annotation in weakly labeled videos. CoRR, 2016, arXiv.org\/abs\/1605.08125","DOI":"10.1109\/ICCV.2015.522"},{"key":"19_CR137","doi-asserted-by":"crossref","unstructured":"L.\u00a0Sun, K.\u00a0Jia, D.-Y. Yeung, B.E. Shi, Human action recognition using factorized spatio-temporal convolutional networks, in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 4597\u20134605","DOI":"10.1109\/ICCV.2015.510"},{"key":"19_CR138","doi-asserted-by":"publisher","unstructured":"J.\u00a0Tompson, Y.L. Murphy\u00a0Stein, K.\u00a0Perlin, Real-time continuous pose recovery of human hands using convolutional networks. ACM-ToG, 33(5), 169:1\u2013169:10 (2014). ISSN 0730-0301. doi: 10.1145\/2629500","DOI":"10.1145\/2629500"},{"key":"19_CR139","doi-asserted-by":"crossref","unstructured":"D.\u00a0Tran, L.\u00a0Bourdev, R.\u00a0Fergus, L.\u00a0Torresani, M.\u00a0Paluri, Learning spatiotemporal features with 3d convolutional networks, in 2015 IEEE International Conference on Computer Vision (ICCV), IEEE, 2015, pp. 4489\u20134497","DOI":"10.1109\/CVPR.2008.4587733"},{"key":"19_CR140","doi-asserted-by":"crossref","unstructured":"P.\u00a0Turaga, A.\u00a0Veeraraghavan, R.\u00a0Chellappa, Statistical analysis on Stiefel and Grassmann manifolds with applications in computer vision, in CVPR, IEEE, 2008, pp. 1\u20138","DOI":"10.1109\/CVPR.2008.4587733"},{"issue":"2","key":"19_CR141","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"J.R. Uijlings, K.E. Van De Sande, T. Gevers, A.W. Smeulders, Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"19_CR142","doi-asserted-by":"crossref","unstructured":"G.\u00a0Varol, I.\u00a0Laptev, C.\u00a0Schmid, Long-term temporal convolutions for action recognition, 2016, arXiv:1604.04494","DOI":"10.1109\/ICCV.2015.460"},{"key":"19_CR143","doi-asserted-by":"crossref","unstructured":"V.\u00a0Veeriah, N.\u00a0Zhuang, G.-J. Qi, Differential recurrent neural networks for action recognition, in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 4041\u20134049","DOI":"10.1109\/ICCV.2015.460"},{"issue":"10","key":"19_CR144","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1007\/s00371-012-0752-6","volume":"29","author":"S Vishwakarma","year":"2013","unstructured":"S. Vishwakarma, A. Agrawal, A survey on activity recognition and behavior understanding in video surveillance. Visual Comput. 29(10), 983\u20131009 (2013)","journal-title":"Visual Comput."},{"key":"19_CR145","unstructured":"C.\u00a0Vondrick, D.\u00a0Ramanan, Video annotation and tracking with active learning, in NIPS, 2011"},{"key":"19_CR146","doi-asserted-by":"crossref","unstructured":"A.\u00a0Waibel, T.\u00a0Hanazawa, G.\u00a0Hinton, K.\u00a0Shikano, K.J. Lang, Phoneme recognition using time-delay neural networks, in Readings in Speech Recognition, 1990, pp. 393\u2013404","DOI":"10.1016\/B978-0-08-051584-7.50037-1"},{"key":"19_CR147","first-page":"1","volume":"119","author":"H Wang","year":"2015","unstructured":"H. Wang, D. Oneata, J. Verbeek, C. Schmid, A robust and efficient video representation for action recognition. Int. J. Comput. Vis. 119, 1\u201320 (2015a)","journal-title":"Int. J. Comput. Vis."},{"key":"19_CR148","doi-asserted-by":"crossref","unstructured":"H.\u00a0Wang, W.\u00a0Wang, L.\u00a0Wang, How scenes imply actions in realistic videos? in ICIP IEEE, 2016a, pp. 1619\u20131623","DOI":"10.1109\/ICIP.2016.7532632"},{"key":"19_CR149","doi-asserted-by":"crossref","unstructured":"J.\u00a0Wang, W.\u00a0Wang, R.\u00a0Wang, W.\u00a0Gao, et\u00a0al., Deep alternative neural network: exploring contexts as early as possible for action recognition, in Advances in Neural Information Processing Systems, 2016b, pp. 811\u2013819","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"19_CR150","doi-asserted-by":"crossref","unstructured":"L.\u00a0Wang, Y.\u00a0Qiao, X.\u00a0Tang, Action recognition with trajectory-pooled deep-convolutional descriptors, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015b, pp. 4305\u20134314","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"19_CR151","unstructured":"L.\u00a0Wang, Z.\u00a0Wang, Y.\u00a0Xiong, Y.\u00a0Qiao, CUHK&SIAT submission for THUMOS15 action recognition challenge, in THUMOS Action Recognition challenge, 2015c, pp. 1\u20133"},{"key":"19_CR152","doi-asserted-by":"crossref","unstructured":"L.\u00a0Wang, Y.\u00a0Xiong, Z.\u00a0Wang, Y.\u00a0Qiao, Towards good practices for very deep two-stream convnets, 2015d, arXiv:1507.02159","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"19_CR153","doi-asserted-by":"crossref","unstructured":"L.\u00a0Wang, Y.\u00a0Xiong, Z.\u00a0Wang, Y.\u00a0Qiao, D.\u00a0Lin, X.\u00a0Tang, L.\u00a0Van\u00a0Gool, Temporal segment networks: towards good practices for deep action recognition, in European Conference on Computer Vision (Springer, New York, 2016c), pp. 20\u201336","DOI":"10.1109\/THMS.2015.2504550"},{"key":"19_CR154","doi-asserted-by":"crossref","unstructured":"P. Wang, W. Li, Z. Gao, J. Zhang, C. Tang, P.O. Ogunbona, Action recognition from depth maps using deep convolutional neural networks. IEEE Trans. Hum.-Mach. Syst. 46(4), 498\u2013509 (2016d)","DOI":"10.1109\/ICPR.2016.7899600"},{"key":"19_CR155","doi-asserted-by":"crossref","unstructured":"P.\u00a0Wang, W.\u00a0Li, S.\u00a0Liu, Y.\u00a0Zhang, Z.\u00a0Gao, P.\u00a0Ogunbona, Large-scale continuous gesture recognition using convolutional neural networks, in Proceedings of International Conference on Pattern RecognitionW, 2016e","DOI":"10.1007\/s12559-016-9388-6"},{"key":"19_CR156","doi-asserted-by":"crossref","unstructured":"P.\u00a0Wang, Q.\u00a0Song, H.\u00a0Han, J.\u00a0Cheng, Sequentially supervised long short-term memory for gesture recognition, in Cognitive Computation, 2016f, pp. 1\u201310","DOI":"10.1007\/s12559-016-9388-6"},{"key":"19_CR157","doi-asserted-by":"crossref","unstructured":"P.\u00a0Wang, W.\u00a0Li, S.\u00a0Liu, Z.\u00a0Gao, C.\u00a0Tang, P.\u00a0Ogunbona, Large-scale isolated gesture recognition using convolutional neural networks, 2017, arXiv:1701.01814","DOI":"10.1109\/ICPR.2016.7899599"},{"key":"19_CR158","doi-asserted-by":"crossref","unstructured":"X.\u00a0Wang, A.\u00a0Farhadi, A.\u00a0Gupta, Actions $$\\tilde{\\,}$$ transformations, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016g, pp. 2658\u20132667","DOI":"10.1109\/CVPR.2016.295"},{"key":"19_CR159","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Wang, M.\u00a0Hoai, Improving human action recognition by non-action classification, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2698\u20132707","DOI":"10.1109\/CVPR.2016.295"},{"key":"19_CR160","doi-asserted-by":"crossref","unstructured":"Y. Wang, J. Song, L. Wang, L. Van Gool, O. Hilliges, Two-stream SR-CNNS for action recognition in videos, BMVC, 2016h","DOI":"10.5244\/C.30.108"},{"key":"19_CR161","doi-asserted-by":"publisher","unstructured":"Z.\u00a0Wang, L.\u00a0Wang, W.\u00a0Du, Y.\u00a0Qiao, Exploring fisher vector and deep networks for action spotting, in CVPRW, 2015e, pp. 10\u201314. doi: 10.1109\/CVPRW.2015.7301330","DOI":"10.1109\/CVPRW.2015.7301330"},{"key":"19_CR162","doi-asserted-by":"crossref","unstructured":"P.\u00a0Weinzaepfel, Z.\u00a0Harchaoui, C.\u00a0Schmid, Learning to track for spatio-temporal action localization, in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 3164\u20133172","DOI":"10.1109\/ICCV.2015.362"},{"key":"19_CR163","doi-asserted-by":"crossref","unstructured":"P. Weinzaepfel, Z. Harchaoui, C. Schmid, Learning to track for spatio-temporal action localization, in ICCV, Santiago, Chile, Dec 2015, arXiv: 1506.01929","DOI":"10.1109\/ICCV.2015.362"},{"issue":"4","key":"19_CR164","doi-asserted-by":"crossref","first-page":"814","DOI":"10.1007\/s12559-014-9299-3","volume":"6","author":"PA Wilson","year":"2014","unstructured":"P.A. Wilson, B. Lewandowska-Tomaszczyk, Affective robotics: modelling and testing cultural prototypes. Cogn. Comput. 6(4), 814\u2013840 (2014)","journal-title":"Cogn. Comput."},{"key":"19_CR165","doi-asserted-by":"publisher","unstructured":"C.\u00a0Wolf, E.\u00a0Lombardi, J.\u00a0Mille, O.\u00a0Celiktutan, M.\u00a0Jiu, E.\u00a0Dogan, G.\u00a0Eren, M.\u00a0Baccouche, E.\u00a0Dellandr\u00e9a, C.-E. Bichot, C.\u00a0Garcia, B.\u00a0Sankur, Evaluation of video activity localizations integrating quality and quantity measurements, in CVIU, vol. 127, Oct 2014, pp. 14\u201330. ISSN 1077-3142. doi: 10.1016\/j.cviu.2014.06.014","DOI":"10.1016\/j.cviu.2014.06.014"},{"key":"19_CR166","doi-asserted-by":"crossref","unstructured":"D.\u00a0Wu, L.\u00a0Pigou, P.J. Kindermans, N.\u00a0Le, L.\u00a0Shao, J.\u00a0Dambre, J.M. Odobez, Deep dynamic neural networks for multimodal gesture segmentation and recognition, in IEEE TPAMI, Feb 2016a","DOI":"10.1109\/TPAMI.2016.2537340"},{"key":"19_CR167","doi-asserted-by":"publisher","unstructured":"J.\u00a0Wu, J.\u00a0Cheng, C.\u00a0Zhao, H.\u00a0Lu, Fusing multi-modal features for gesture recognition, in ICMI, 2013, pp. 453\u2013460. ISBN 978-1-4503-2129-7. doi: 10.1145\/2522848.2532589","DOI":"10.1145\/2522848.2532589"},{"key":"19_CR168","doi-asserted-by":"crossref","unstructured":"J.\u00a0Wu, P.\u00a0Ishwar, J.\u00a0Konrad, Two-stream CNNS for gesture-based verification and identification: learning user style, in CVPRW, 2016b","DOI":"10.1109\/CVPRW.2016.21"},{"key":"19_CR169","unstructured":"J.\u00a0Wu, G.\u00a0Wang, W.\u00a0Yang, X.\u00a0Ji, Action recognition with joint attention on multi-level deep features, 2016c, arXiv:1607.02556"},{"key":"19_CR170","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Wu, Y.\u00a0Fu, Y.-G. Jiang, L.\u00a0Sigal, Harnessing object and scene semantics for large-scale video understanding, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016d, pp. 3112\u20133121","DOI":"10.1109\/CVPR.2016.339"},{"key":"19_CR171","doi-asserted-by":"crossref","unstructured":"X.\u00a0Xu, T.M. Hospedales, S.\u00a0Gong, Multi-task zero-shot action recognition with prioritised data augmentation, in Proceedings of European Conference on Computer Vision, 2016","DOI":"10.1007\/978-3-319-46475-6_22"},{"key":"19_CR172","unstructured":"Z.\u00a0Xu, L.\u00a0Zhu, Y.\u00a0Yang, A.G. Hauptmann, UTS-CMU at THUMOS 2015, in CVPR THUMOS Challenge, 2015a"},{"key":"19_CR173","unstructured":"Z.\u00a0Xu, L.\u00a0Zhu, Y.\u00a0Yang, A.G. Hauptmann, UTS-CMU at THUMOS, 2015b"},{"key":"19_CR174","doi-asserted-by":"crossref","unstructured":"J.\u00a0Yamato, J.\u00a0Ohya, K.\u00a0Ishii, Recognizing human action in time-sequential images using hidden Markov model, in 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1992. Proceedings CVPR\u201992, IEEE, 1992, pp. 379\u2013385","DOI":"10.1109\/CVPR.1992.223161"},{"key":"19_CR175","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Ye, Y.\u00a0Tian, Embedding sequential information into spatiotemporal features for action recognition, in CVPRW, 2016","DOI":"10.1109\/CVPRW.2016.142"},{"key":"19_CR176","doi-asserted-by":"crossref","unstructured":"S.\u00a0Yeung, O.\u00a0Russakovsky, G.\u00a0Mori, L.\u00a0Fei-Fei, End-to-end learning of action detection from frame glimpses in videos, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2678\u20132687","DOI":"10.1109\/CVPR.2016.293"},{"key":"19_CR177","volume-title":"An introduction to computational networks and the computational network toolkit","author":"D Yu","year":"2014","unstructured":"D. Yu, A. Eversole, M. Seltzer, K. Yao, Z. Huang, B. Guenter, O. Kuchaiev, Y. Zhang, F. Seide, H. Wang et al., An introduction to computational networks and the computational network toolkit (Technical Report, TR MSR, 2014)"},{"key":"19_CR178","doi-asserted-by":"crossref","unstructured":"J.\u00a0Yu, K.\u00a0Weng, G.\u00a0Liang, G.\u00a0Xie, A vision-based robotic grasping system using deep learning for 3d object recognition and pose estimation, in 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO), IEEE, 2013, pp. 1175\u20131180","DOI":"10.1109\/ROBIO.2013.6739623"},{"key":"19_CR179","doi-asserted-by":"crossref","unstructured":"J.\u00a0Yuan, B.\u00a0Ni, X.\u00a0Yang, A.\u00a0Kassim, Temporal action localization with pyramid of score distribution features, in CVPR, 2016","DOI":"10.1109\/CVPR.2016.337"},{"key":"19_CR180","doi-asserted-by":"crossref","unstructured":"J.\u00a0Yue-Hei\u00a0Ng, M.\u00a0Hausknecht, S.\u00a0Vijayanarasimhan, O.\u00a0Vinyals, R.\u00a0Monga, G.\u00a0Toderici, Beyond short snippets: deep networks for video classification, in CVPR, 2015, pp. 4694\u20134702","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"19_CR181","doi-asserted-by":"crossref","unstructured":"S.\u00a0Zha, F.\u00a0Luisier, W.\u00a0Andrews, N.\u00a0Srivastava, R.\u00a0Salakhutdinov, Exploiting image-trained cnn architectures for unconstrained video classification, 2015, arXiv:1503.04144","DOI":"10.5244\/C.29.60"},{"key":"19_CR182","doi-asserted-by":"crossref","unstructured":"B.\u00a0Zhang, L.\u00a0Wang, Z.\u00a0Wang, Y.\u00a0Qiao, H.\u00a0Wang, Real-time action recognition with enhanced motion vector CNNS, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2718\u20132726","DOI":"10.1109\/CVPR.2016.297"},{"key":"19_CR183","unstructured":"B.\u00a0Zhou, A.\u00a0Lapedriza, J.\u00a0Xiao, A.\u00a0Torralba, A.\u00a0Oliva, Learning deep features for scene recognition using places database, in NIPS, 2014, pp. 487\u2013495"},{"key":"19_CR184","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neucom.2016.04.007","volume":"201","author":"T Zhou","year":"2016","unstructured":"T. Zhou, N. Li, X. Cheng, Q. Xu, L. Zhou, Z. Wu, Learning semantic context feature-tree for action recognition via nearest neighbor fusion. Neurocomputing 201, 1\u201311 (2016)","journal-title":"Neurocomputing"},{"key":"19_CR185","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Zhou, B.\u00a0Ni, R.\u00a0Hong, M.\u00a0Wang, Q.\u00a0Tian, Interaction part mining: a mid-level approach for fine-grained action recognition, in CVPR, 2015, pp. 3323\u20133331","DOI":"10.1109\/CVPR.2015.7298953"},{"key":"19_CR186","doi-asserted-by":"crossref","unstructured":"G.\u00a0Zhu, L.\u00a0Zhang, L.\u00a0Mei, J.\u00a0Shao, J.\u00a0Song, P.\u00a0Shen, Large-scale isolated gesture recognition using pyramidal 3d convolutional networks, in Proceedings of International Conference on Pattern RecognitionW, 2016a","DOI":"10.1109\/ICPR.2016.7899601"},{"key":"19_CR187","doi-asserted-by":"crossref","unstructured":"W.\u00a0Zhu, J.\u00a0Hu, G.\u00a0Sun, X.\u00a0Cao, Y.\u00a0Qiao, A key volume mining deep framework for action recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016b, pp. 1991\u20131999","DOI":"10.1109\/CVPR.2016.219"},{"key":"19_CR188","doi-asserted-by":"crossref","unstructured":"C.L. Zitnick, P.\u00a0Doll\u00e1r, Edge boxes: locating object proposals from edges, in European Conference on Computer Vision (Springer, New York, 2014), pp. 391\u2013405","DOI":"10.1007\/978-3-319-10602-1_26"}],"container-title":["The Springer Series on Challenges in Machine Learning","Gesture Recognition"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-57021-1_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T15:09:20Z","timestamp":1750777760000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-57021-1_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319570204","9783319570211"],"references-count":188,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-57021-1_19","relation":{},"ISSN":["2520-131X","2520-1328"],"issn-type":[{"value":"2520-131X","type":"print"},{"value":"2520-1328","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}