{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T09:09:42Z","timestamp":1742980182766,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030110116"},{"type":"electronic","value":"9783030110123"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-11012-3_40","type":"book-chapter","created":{"date-parts":[[2019,1,28]],"date-time":"2019-01-28T17:50:19Z","timestamp":1548697819000},"page":"534-548","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Residual Stacked RNNs for Action Recognition"],"prefix":"10.1007","author":[{"given":"Mohamed Ilyes","family":"Lakhal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Albert","family":"Clap\u00e9s","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergio","family":"Escalera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oswald","family":"Lanz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Cavallaro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,29]]},"reference":[{"key":"40_CR1","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: The IEEE International Conference on Computer Vision, ICCV, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"issue":"2\u20133","key":"40_CR2","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I.: On space-time interest points. Int. J. Comput. Vis. 64(2\u20133), 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2017","DOI":"10.1109\/CVPR.2017.502"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"issue":"1","key":"40_CR5","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR6","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, December 2014"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"issue":"6","key":"40_CR8","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"G Varol","year":"2018","unstructured":"Varol, G., Laptev, I., Schmid, C.: Long-term temporal convolutions for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1510\u20131517 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2712608","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2016","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"40_CR10","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."},{"key":"40_CR11","unstructured":"Ng, J.Y.-H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2015"},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"Kim, J., El-Khamy, M., Lee, J.: Residual LSTM: design of a deep recurrent architecture for distant speech recognition. arXiv preprint arXiv:1701.03360 (2017)","DOI":"10.21437\/Interspeech.2017-477"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: IEEE International Conference on Computer Vision, December 2015","DOI":"10.1109\/ICCV.2015.510"},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.: ActionVLAD: learning spatio-temporal aggregation for action classification. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2017","DOI":"10.1109\/CVPR.2017.337"},{"key":"40_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/978-3-642-25446-8_4","volume-title":"Human Behavior Understanding","author":"M Baccouche","year":"2011","unstructured":"Baccouche, M., Mamalet, F., Wolf, C., Garcia, C., Baskurt, A.: Sequential deep learning for human action recognition. In: Salah, A.A., Lepri, B. (eds.) HBU 2011. LNCS, vol. 7065, pp. 29\u201339. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-25446-8_4"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"40_CR17","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555 (2014)"},{"key":"40_CR18","doi-asserted-by":"crossref","unstructured":"Asadi-Aghbolaghi, M., et al.: A survey on deep learning based approaches for action and gesture recognition in image sequences. In: IEEE International Conference on Automatic Face & Gesture Recognition, pp. 476\u2013483 (2017)","DOI":"10.1109\/FG.2017.150"},{"key":"40_CR19","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W., Woo, W.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in Neural Information Processing Systems, December 2015"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Lanz, O.: Convolutional long short-term memory networks for recognizing first person interactions. In: IEEE International Conference on Computer Vision Workshops, October 2017","DOI":"10.1109\/ICCVW.2017.276"},{"key":"40_CR21","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","volume":"166","author":"Z Li","year":"2018","unstructured":"Li, Z., Gavrilyuk, K., Gavves, E., Jain, M., Snoek, C.G.: VideoLSTM convolves, attends and flows for action recognition. Comput. Vis. Image Underst. 166, 41\u201350 (2018)","journal-title":"Comput. Vis. Image Underst."},{"key":"40_CR22","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"40_CR23","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. arXiv preprint arXiv:1511.04119 (2015)"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Sun, L., Jia, K., Chen, K., Yeung, D.Y., Shi, B.E., Savarese, S.: Lattice long short-term memory for human action recognition. In: IEEE International Conference on Computer Vision, October 2017","DOI":"10.1109\/ICCV.2017.236"},{"key":"40_CR25","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1109\/TCSVT.2013.2270402","volume":"23","author":"PVK Borges","year":"2013","unstructured":"Borges, P.V.K., Conci, N., Cavallaro, A.: Video-based human behavior understanding: a survey. IEEE Trans. Circ. Syst. Video Technol. 23, 1993\u20132008 (2013)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"40_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"40_CR27","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, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"40_CR28","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: bridging the gap between human and machine translation. CoRR (2016)"},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: IEEE International Conference on Computer Vision, November 2011","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"40_CR30","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. CoRR (2012)"},{"key":"40_CR31","unstructured":"Tijmen, T., Geoffrey, H.: Lecture 6.5-RmsProp: divide the gradient by a running average of its recent magnitude. In: COURSERA: Neural Networks for Machine Learning (2012)"},{"key":"40_CR32","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In: The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, June 2018","DOI":"10.1109\/CVPR.2018.00685"},{"key":"40_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-030-01225-0_18","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Diba","year":"2018","unstructured":"Diba, A., et al.: Spatio-temporal channel correlation networks for action classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 299\u2013315. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_18"},{"key":"40_CR34","doi-asserted-by":"crossref","unstructured":"Yang, X., Molchanov, P., Kautz, J.: Making convolutional networks recurrent for visual sequence learning. In: The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, June 2018","DOI":"10.1109\/CVPR.2018.00677"},{"key":"40_CR35","unstructured":"Ng, J.Y.H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2015"},{"key":"40_CR36","doi-asserted-by":"crossref","unstructured":"Sun, L., Jia, K., Yeung, D.Y., Shi, B.E.: Human action recognition using factorized spatio-temporal convolutional networks. In: Proceedings of the 2015 IEEE International Conference on Computer Vision, ICCV, ICCV 2015, Washington, DC, USA, pp. 4597\u20134605. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.522"},{"key":"40_CR37","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2015","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"40_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, W., Hu, J., Sun, G., Cao, X., Qiao, Y.: A key volume mining deep framework for action recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 1991\u20131999, June 2016","DOI":"10.1109\/CVPR.2016.219"},{"issue":"99","key":"40_CR39","first-page":"1","volume":"PP","author":"G Varol","year":"2017","unstructured":"Varol, G., Laptev, I., Schmid, C.: Long-term temporal convolutions for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 1 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR40","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.: Spatiotemporal residual networks for video action recognition. In: Advances in Neural Information Processing Systems, pp. 3468\u20133476 (2016)","DOI":"10.1109\/CVPR.2017.787"},{"key":"40_CR41","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal multiplier networks for video action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, July 2017","DOI":"10.1109\/CVPR.2017.787"},{"issue":"4","key":"40_CR42","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume":"39","author":"J Donahue","year":"2017","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 677\u2013691 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR43","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: Blei, D., Bach, F. (eds.) Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, JMLR Workshop and Conference Proceedings, pp. 843\u2013852 (2015)"},{"key":"40_CR44","doi-asserted-by":"crossref","unstructured":"Mahasseni, B., Todorovic, S.: 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, pp. 3054\u20133062 (2016)","DOI":"10.1109\/CVPR.2016.333"},{"key":"40_CR45","doi-asserted-by":"crossref","unstructured":"Choi, K., Fazekas, G., Sandler, M., Cho, K.: Convolutional recurrent neural networks for music classification. In: IEEE International Conference on Acoustics, Speech and Signal Processing, March 2017","DOI":"10.1109\/ICASSP.2017.7952585"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11012-3_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T03:17:26Z","timestamp":1674875846000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11012-3_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110116","9783030110123"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11012-3_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"29 January 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}