{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T20:40:41Z","timestamp":1725914441733},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319700953"},{"type":"electronic","value":"9783319700960"}],"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\/978-3-319-70096-0_16","type":"book-chapter","created":{"date-parts":[[2017,10,25]],"date-time":"2017-10-25T01:33:18Z","timestamp":1508895198000},"page":"147-156","source":"Crossref","is-referenced-by-count":6,"title":["Comparing Hybrid NN-HMM and RNN for Temporal Modeling in Gesture Recognition"],"prefix":"10.1007","author":[{"given":"Nicolas","family":"Granger","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moun\u00eem A.","family":"el Yacoubi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,26]]},"reference":[{"key":"16_CR1","unstructured":"Bourlard, H., Morgan, N.: A continuous speech recognition system embedding MLP into HMM. In: Advances in Neural Information Processing Systems, pp. 186\u2013193 (1990)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"16_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/978-3-319-16178-5_32","volume-title":"Computer Vision - ECCV 2014 Workshops","author":"S Escalera","year":"2015","unstructured":"Escalera, S., Bar\u00f3, X., Gonz\u00e0lez, J., Bautista, M.A., Madadi, M., Reyes, M., Ponce-L\u00f3pez, V., Escalante, H.J., Shotton, J., Guyon, I.: ChaLearn looking at people challenge 2014: dataset and results. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8925, pp. 459\u2013473. Springer, Cham (2015). doi: 10.1007\/978-3-319-16178-5_32"},{"key":"16_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1007\/11550907_126","volume-title":"Artificial Neural Networks: Formal Models and Their Applications \u2013 ICANN 2005","author":"A Graves","year":"2005","unstructured":"Graves, A., Fern\u00e1ndez, S., Schmidhuber, J.: Bidirectional LSTM networks for improved phoneme classification and recognition. In: Duch, W., Kacprzyk, J., Oja, E., Zadro\u017cny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 799\u2013804. Springer, Heidelberg (2005). doi: 10.1007\/11550907_126"},{"key":"16_CR5","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"},{"key":"16_CR6","unstructured":"Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: Advances in Neural Information Processing Systems, pp. 545\u2013552 (2009)"},{"issue":"8","key":"16_CR7","doi-asserted-by":"crossref","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."},{"key":"16_CR8","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Bach, F., Blei, D. (eds.) Proceedings of the 32nd International Conference on Machine Learning, Proceedings of Machine Learning Research, vol. 37, pp. 448\u2013456, 07\u201309 July 2015. PMLR, Lille (2015)"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Koller, O., Zargaran, S., Ney, H., Bowden, R.: Deep sign: hybrid CNN-HMM for continuous sign language recognition. In: Proceedings of the British Machine Vision Conference 2016, BMVC 2016, York, UK, 19\u201322 September 2016 (2016)","DOI":"10.5244\/C.30.136"},{"key":"16_CR10","unstructured":"Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: ICML Workshop on Deep Learning for Audio, Speech and Language Processing (2013)"},{"key":"16_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-319-16178-5_33","volume-title":"Computer Vision - ECCV 2014 Workshops","author":"N Neverova","year":"2015","unstructured":"Neverova, N., Wolf, C., Taylor, G.W., Nebout, F.: Multi-scale deep learning for gesture detection and localization. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8925, pp. 474\u2013490. Springer, Cham (2015). doi: 10.1007\/978-3-319-16178-5_33"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Pigou, L., van den Oord, A., Dieleman, S., Van Herreweghe, M., Dambre, J.: Beyond temporal pooling: recurrence and temporal convolutions for gesture recognition in Video. Int. J. Comput. Vis. 1\u201310 (2016)","DOI":"10.1007\/s11263-016-0957-7"},{"issue":"1","key":"16_CR13","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"16_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/11550822_93","volume-title":"Artificial Neural Networks: Biological Inspirations \u2013 ICANN 2005","author":"L T\u00f3th","year":"2005","unstructured":"T\u00f3th, L., Kocsor, A.: Training HMM\/ANN hybrid speech recognizers by probabilistic sampling. In: Duch, W., Kacprzyk, J., Oja, E., Zadro\u017cny, S. (eds.) ICANN 2005. LNCS, vol. 3696, pp. 597\u2013603. Springer, Heidelberg (2005). doi: 10.1007\/11550822_93"},{"issue":"8","key":"16_CR16","doi-asserted-by":"publisher","first-page":"1583","DOI":"10.1109\/TPAMI.2016.2537340","volume":"38","author":"D Wu","year":"2016","unstructured":"Wu, D., Pigou, L., Kindermans, P.J., Nam, L.E., Shao, L., Dambre, J., Odobez, J.M.: Deep Dynamic Neural Networks for Multimodal Gesture Segmentation and Recognition. IEEE Trans. Pattern Anal. Mach. Intell. 38(8), 1583\u20131597 (2016). doi: 10.1109\/TPAMI.2016.2537340","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"16_CR17","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1109\/TPAMI.2008.172","volume":"31","author":"HD Yang","year":"2009","unstructured":"Yang, H.D., Sclaroff, S., Lee, S.W.: Sign language spotting with a threshold model based on conditional random fields. IEEE Trans. Patt. Anal. Mach. Intell. 31(7), 1264\u20131277 (2009)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Yin, Y., Davis, R.: Real-time continuous gesture recognition for natural human-computer interaction. In: 2014 IEEE Symposium on Visual Languages and Human-Centric Computing (VL\/HCC), pp. 113\u2013120. IEEE (2014)","DOI":"10.1109\/VLHCC.2014.6883032"},{"key":"16_CR19","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. CoRR abs\/1511.07122 (2015)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-70096-0_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,5]],"date-time":"2019-10-05T03:29:29Z","timestamp":1570246169000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-70096-0_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319700953","9783319700960"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-70096-0_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}