{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:51:38Z","timestamp":1775245898179,"version":"3.50.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012632","type":"print"},{"value":"9783030012649","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01264-9_41","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T04:20:53Z","timestamp":1538972453000},"page":"693-710","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Human Motion Analysis with Deep Metric Learning"],"prefix":"10.1007","author":[{"given":"Huseyin","family":"Coskun","sequence":"first","affiliation":[]},{"given":"David Joseph","family":"Tan","sequence":"additional","affiliation":[]},{"given":"Sailesh","family":"Conjeti","sequence":"additional","affiliation":[]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[]},{"given":"Federico","family":"Tombari","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"41_CR1","unstructured":"Carnegie mellon university - CMU graphics lab - motion capture library (2010). http:\/\/mocap.cs.cmu.edu\/. Accessed 03 Nov 2018"},{"key":"41_CR2","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https:\/\/www.tensorflow.org\/. Software available from tensorflow.org"},{"key":"41_CR3","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. CoRR abs\/1607.06450 (2016). http:\/\/arxiv.org\/abs\/1607.06450"},{"key":"41_CR4","unstructured":"Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: KDD Workshop, Seattle, WA, vol. 10, pp. 359\u2013370 (1994)"},{"key":"41_CR5","unstructured":"Che, Z., He, X., Xu, K., Liu, Y.: DECADE: a deep metric learning model for multivariate time series (2017)"},{"issue":"11","key":"41_CR6","doi-asserted-by":"publisher","first-page":"1676","DOI":"10.1109\/TVCG.2010.272","volume":"17","author":"C Chen","year":"2011","unstructured":"Chen, C., Zhuang, Y., Nie, F., Yang, Y., Wu, F., Xiao, J.: Learning a 3D human pose distance metric from geometric pose descriptor. IEEE Trans. Vis. Comput. Graph. 17(11), 1676\u20131689 (2011)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 539\u2013546. IEEE (2005)","DOI":"10.1109\/CVPR.2005.202"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.601"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Cuturi, M., Vert, J.P., Birkenes, O., Matsui, T.: A kernel for time series based on global alignments. In: 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2007, vol. 2, pp. II\u2013413. IEEE (2007)","DOI":"10.1109\/ICASSP.2007.366260"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: Proceedings of the 24th International Conference on Machine Learning, pp. 209\u2013216. ACM (2007)","DOI":"10.1145\/1273496.1273523"},{"issue":"3","key":"41_CR11","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1016\/S0959-440X(96)80056-X","volume":"6","author":"SR Eddy","year":"1996","unstructured":"Eddy, S.R.: Hidden markov models. Curr. Opin. Struct. Biol. 6(3), 361\u2013365 (1996)","journal-title":"Curr. Opin. Struct. Biol."},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6645\u20136649. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"issue":"10","key":"41_CR13","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","volume":"28","author":"K Greff","year":"2017","unstructured":"Greff, K., Srivastava, R.K., Koutn\u00edk, J., Steunebrink, B.R., Schmidhuber, J.: LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28(10), 2222\u20132232 (2017)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"41_CR14","first-page":"723","volume":"13","author":"A Gretton","year":"2012","unstructured":"Gretton, A., Borgwardt, K.M., Rasch, M.J., Sch\u00f6lkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. 13, 723\u2013773 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1735\u20131742. IEEE (2006)","DOI":"10.1109\/CVPR.2006.100"},{"issue":"8","key":"41_CR16","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"7","key":"41_CR17","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Patt. Anal. Mach. Intell. 36(7), 1325\u20131339 (2014)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"41_CR18","doi-asserted-by":"crossref","unstructured":"Keogh, E.J., Pazzani, M.J.: Derivative dynamic time warping. In: Proceedings of the 2001 SIAM International Conference on Data Mining, pp. 1\u201311. SIAM (2001)","DOI":"10.1137\/1.9781611972719.1"},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Laurent, C., Pereyra, G., Brakel, P., Zhang, Y., Bengio, Y.: Batch normalized recurrent neural networks. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2657\u20132661. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472159"},{"key":"41_CR20","unstructured":"Li, Y., Swersky, K., Zemel, R.: Generative moment matching networks. In: Proceedings of the 32nd International Conference on Machine Learning (ICML 2015), pp. 1718\u20131727 (2015)"},{"key":"41_CR21","unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. In: Proceedings of International Conference on Learning Representations (ICLR) (2017)"},{"key":"41_CR22","doi-asserted-by":"crossref","unstructured":"L\u00f3pez-M\u00e9ndez, A., Gall, J., Casas, J.R., Van Gool, L.J.: Metric learning from poses for temporal clustering of human motion. In: BMVC, pp. 1\u201312 (2012)","DOI":"10.5244\/C.26.49"},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"Martinez, J., Black, M.J., Romero, J.: On human motion prediction using recurrent neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.497"},{"issue":"4","key":"41_CR24","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1145\/3072959.3073596","volume":"36","author":"D Mehta","year":"2017","unstructured":"Mehta, D., et al.: VNect: real-time 3D human pose estimation with a single RGB camera. ACM Trans. Graph. (TOG) 36(4), 44 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"6","key":"41_CR25","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.1109\/TCYB.2015.2426723","volume":"46","author":"J Mei","year":"2016","unstructured":"Mei, J., Liu, M., Wang, Y.F., Gao, H.: Learning a mahalanobis distance-based dynamic time warping measure for multivariate time series classification. IEEE Trans. Cybern. 46(6), 1363\u20131374 (2016)","journal-title":"IEEE Trans. Cybern."},{"key":"41_CR26","unstructured":"Mishchuk, A., Mishkin, D., Radenovic, F., Matas, J.: Working hard to know your neighbor\u2019s margins: local descriptor learning loss. In: Proceedings Conference on Neural Information Processing Systems (NIPS), December 2017"},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Movshovitz-Attias, Y., Toshev, A., Leung, T.K., Ioffe, S., Singh, S.: No fuss distance metric learning using proxies. In: The IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.47"},{"key":"41_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"41_CR29","unstructured":"Pei, W., Tax, D.M., van der Maaten, L.: Modeling time series similarity with siamese recurrent networks. CoRR abs\/1603.04713 (2016)"},{"key":"41_CR30","doi-asserted-by":"crossref","unstructured":"Ratanamahatana, C.A., Keogh, E.: Making time-series classification more accurate using learned constraints. In: SIAM (2004)","DOI":"10.1137\/1.9781611972740.2"},{"key":"41_CR31","unstructured":"Rippel, O., Paluri, M., Dollar, P., Bourdev, L.: Metric learning with adaptive density discrimination. In: International Conference on Learning Representations (2016)"},{"key":"41_CR32","first-page":"513","volume":"17","author":"S Roweis","year":"2004","unstructured":"Roweis, S., Hinton, G., Salakhutdinov, R.: Neighbourhood component analysis. Adv. Neural Inf. Process. Syst. (NIPS) 17, 513\u2013520 (2004)","journal-title":"Adv. Neural Inf. Process. Syst. (NIPS)"},{"key":"41_CR33","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"41_CR34","unstructured":"Schultz, M., Joachims, T.: Learning a distance metric from relative comparisons. In: Advances in Neural Information Processing Systems, pp. 41\u201348 (2004)"},{"key":"41_CR35","unstructured":"Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: Advances in Neural Information Processing Systems, pp. 1857\u20131865 (2016)"},{"key":"41_CR36","doi-asserted-by":"crossref","unstructured":"Song, H.O., Xiang, Y., Jegelka, S., Savarese, S.: Deep metric learning via lifted structured feature embedding. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4004\u20134012. IEEE (2016)","DOI":"10.1109\/CVPR.2016.434"},{"key":"41_CR37","doi-asserted-by":"crossref","unstructured":"Sun, X., Shang, J., Liang, S., Wei, Y.: Compositional human pose regression. In: The IEEE International Conference on Computer Vision (ICCV), vol. 2 (2017)","DOI":"10.1109\/ICCV.2017.284"},{"key":"41_CR38","unstructured":"Sutherland, D.J., et al.: Generative models and model criticism via optimized maximum mean discrepancy. In: Proceedings of the 32nd International Conference on Machine Learning (ICML 2017) (2017)"},{"key":"41_CR39","doi-asserted-by":"crossref","unstructured":"Taylor, G.W., Hinton, G.E., Roweis, S.T.: Modeling human motion using binary latent variables. In: Advances in Neural Information Processing Systems, pp. 1345\u20131352 (2007)","DOI":"10.7551\/mitpress\/7503.003.0173"},{"key":"41_CR40","doi-asserted-by":"crossref","unstructured":"Tian, B.F.Y., Wu, F.: L2-Net: deep learning of discriminative patch descriptor in Euclidean space. In: Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2 (2017)","DOI":"10.1109\/CVPR.2017.649"},{"key":"41_CR41","doi-asserted-by":"publisher","first-page":"1128","DOI":"10.1109\/TPAMI.2017.2710047","volume":"5","author":"G Trigeorgis","year":"2018","unstructured":"Trigeorgis, G., Nicolaou, M.A., Schuller, B.W., Zafeiriou, S.: Deep canonical time warping for simultaneous alignment and representation learning of sequences. IEEE Trans. Patt. Anal. Mach. Intell. 5, 1128\u20131138 (2018)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"issue":"1","key":"41_CR42","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/BF01074755","volume":"4","author":"TK Vintsyuk","year":"1968","unstructured":"Vintsyuk, T.K.: Speech discrimination by dynamic programming. Cybernetics 4(1), 52\u201357 (1968)","journal-title":"Cybernetics"},{"key":"41_CR43","doi-asserted-by":"crossref","unstructured":"Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. In: The IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.144"},{"key":"41_CR44","doi-asserted-by":"crossref","unstructured":"Yin, X., Chen, Q.: Deep metric learning autoencoder for nonlinear temporal alignment of human motion. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 2160\u20132166. IEEE (2016)","DOI":"10.1109\/ICRA.2016.7487366"},{"key":"41_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, X., Yu, F.X., Kumar, S., Chang, S.F.: Learning spread-out local feature descriptors. In: The IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.492"},{"key":"41_CR46","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1007\/978-3-319-18032-8_42","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"Y Zheng","year":"2015","unstructured":"Zheng, Y., Liu, Q., Chen, E., Zhao, J.L., He, L., Lv, G.: Convolutional nonlinear neighbourhood components analysis for time series classification. In: Cao, T., Lim, E.-P., Zhou, Z.-H., Ho, T.-B., Cheung, D., Motoda, H. (eds.) PAKDD 2015. LNCS (LNAI), vol. 9078, pp. 534\u2013546. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-18032-8_42"},{"key":"41_CR47","unstructured":"Zhou, F., Torre, F.: Canonical time warping for alignment of human behavior. In: Advances in Neural Information Processing Systems, pp. 2286\u20132294 (2009)"},{"issue":"2","key":"41_CR48","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/TPAMI.2015.2414429","volume":"38","author":"F Zhou","year":"2016","unstructured":"Zhou, F., De la Torre, F.: Generalized canonical time warping. IEEE Trans. Patt. Anal. Mach. Intell. 38(2), 279\u2013294 (2016)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01264-9_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:53:51Z","timestamp":1775242431000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01264-9_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012632","9783030012649"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01264-9_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}