{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T08:10:20Z","timestamp":1768551020653,"version":"3.49.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030412982","type":"print"},{"value":"9783030412999","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-41299-9_24","type":"book-chapter","created":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T09:02:51Z","timestamp":1582362171000},"page":"307-320","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Using Deep Convolutional LSTM Networks for Learning Spatiotemporal Features"],"prefix":"10.1007","author":[{"given":"Logan","family":"Courtney","sequence":"first","affiliation":[]},{"given":"Ramavarapu","family":"Sreenivas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,2,23]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Deep audio-visual speech recognition. arXiv e-prints, September 2018","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Zisserman, A.: Deep lip reading: a comparison of models and an online application. arXiv e-prints, June 2018","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"24_CR3","unstructured":"Afouras, T., Chung, J.S., Zisserman, A.: LRS3-TED: a large-scale dataset for visual speech recognition. arXiv e-prints, September 2018"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"24_CR5","unstructured":"Bian, Y., et al.: Revisiting the effectiveness of off-the-shelf temporal modeling approaches for large-scale video classification. CoRR abs\/1708.03805 (2017)"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Lip reading sentences in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.367"},{"key":"24_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-54184-6_6","volume-title":"Computer Vision \u2013 ACCV 2016","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 87\u2013103. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_6"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in profile. In: British Machine Vision Conference (2017)","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Conneau, A., Schwenk, H., Barrault, L., LeCun, Y.: Very deep convolutional networks for natural language processing. CoRR abs\/1606.01781 (2016)","DOI":"10.18653\/v1\/E17-1104"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Cotterell, R., Mielke, S.J., Eisner, J., Roark, B.: Are all languages equally hard to language-model? In: NAACL-HLT (2018)","DOI":"10.18653\/v1\/N18-2085"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, ICML 2006, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"24_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-030-11012-3_24","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"A Hanson","year":"2019","unstructured":"Hanson, A., Pnvr, K., Krishnagopal, S., Davis, L.: Bidirectional convolutional LSTM for the detection of violence in videos. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11130, pp. 280\u2013295. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11012-3_24"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and imagenet? CoRR abs\/1711.09577 (2017)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs\/1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"24_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."},{"key":"24_CR17","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 International Computer Vision and Pattern Recognition (CVPR 2014) (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"24_CR18","unstructured":"Kay, W., et al.: The kinetics human action video dataset. CoRR abs\/1705.06950 (2017)"},{"key":"24_CR19","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs\/1412.6980 (2014)"},{"key":"24_CR20","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097\u20131105. Curran Associates, Inc. (2012)"},{"key":"24_CR21","unstructured":"Luo, W., Li, Y., Urtasun, R., Zemel, R.S.: Understanding the effective receptive field in deep convolutional neural networks. CoRR abs\/1701.04128 (2017)"},{"key":"24_CR22","unstructured":"Ng, J.Y.H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: Computer Vision and Pattern Recognition (2015)"},{"key":"24_CR23","unstructured":"Pascanu, R., Mikolov, T., Bengio, Y.: Understanding the exploding gradient problem. CoRR abs\/1211.5063 (2012)"},{"key":"24_CR24","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch (2017)"},{"issue":"3","key":"24_CR25","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"24_CR26","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D., Wong, W., Woo, W.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. CoRR abs\/1506.04214 (2015)"},{"key":"24_CR27","unstructured":"Shillingford, B., et al.: Large-scale visual speech recognition. CoRR abs\/1807.05162 (2018)"},{"key":"24_CR28","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 27, pp. 568\u2013576. Curran Associates, Inc. (2014)"},{"key":"24_CR29","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Stafylakis, T., Khan, M.H., Tzimiropoulos, G.: Pushing the boundaries of audiovisual word recognition using residual networks and LSTMs. CoRR abs\/1811.01194 (2018)","DOI":"10.1016\/j.cviu.2018.10.003"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Stafylakis, T., Tzimiropoulos, G.: Combining residual networks with LSTMs for lipreading. CoRR abs\/1703.04105 (2017)","DOI":"10.21437\/Interspeech.2017-85"},{"key":"24_CR32","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 27, pp. 3104\u20133112. Curran Associates, Inc. (2014)"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impact of residual connections on learning. CoRR abs\/1602.07261 (2016)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"24_CR35","unstructured":"Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: C3D: generic features for video analysis. CoRR abs\/1412.0767 (2014)"},{"key":"24_CR36","unstructured":"Vaswani, A., et al.: Attention is all you need. CoRR abs\/1706.03762 (2017)"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yang, D., Dyer, C., He, X., Smola, A.J., Hovy, E.H.: Hierarchical attention networks for document classification. In: HLT-NAACL (2016)","DOI":"10.18653\/v1\/N16-1174"},{"key":"24_CR38","unstructured":"Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. CoRR abs\/1409.2329 (2014)"},{"key":"24_CR39","doi-asserted-by":"publisher","unstructured":"Zhang, L., Zhu, G., Shen, P., Song, J.: Learning spatiotemporal features using 3DCNN and convolutional LSTM for gesture recognition, pp. 3120\u20133128, October 2017. https:\/\/doi.org\/10.1109\/ICCVW.2017.369","DOI":"10.1109\/ICCVW.2017.369"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-41299-9_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T08:10:56Z","timestamp":1665907856000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-41299-9_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030412982","9783030412999"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-41299-9_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"23 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2019a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acpr2019.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"214","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"125","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"58% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"for ACPR 2019 Workshops volume accepted 17 full papers and 6 short papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}