{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T11:45:17Z","timestamp":1793619917928,"version":"4.5.0"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197710","type":"print"},{"value":"9783031197727","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19772-7_22","type":"book-chapter","created":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T18:09:58Z","timestamp":1666894198000},"page":"369-385","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Continual 3D Convolutional Neural Networks for\u00a0Real-time Processing of\u00a0Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2841-864X","authenticated-orcid":false,"given":"Lukas","family":"Hedegaard","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4807-1345","authenticated-orcid":false,"given":"Alexandros","family":"Iosifidis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,28]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: ViViT: a video vision transformer. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Z., He, X., Sun, J., Vasconcelos, N.: Deep learning with low precision by half-wave gaussian quantization. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5406\u20135414 (2017)","DOI":"10.1109\/CVPR.2017.574"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"22_CR4","unstructured":"Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., Zisserman, A.: A short note about kinetics-600. preprint, arXiv:1808.01340 (2018)"},{"key":"22_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1007\/978-3-030-01225-0_40","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Carreira","year":"2018","unstructured":"Carreira, J., P\u0103tr\u0103ucean, V., Mazare, L., Zisserman, A., Osindero, S.: Massively parallel video networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 680\u2013697. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_40"},{"key":"22_CR6","unstructured":"Chen, W., Wilson, J.T., Tyree, S., Weinberger, K.Q., Chen, Y.: Compressing neural networks with the hashing trick. In: International Conference on International Conference on Machine Learning (ICML), pp. 2285\u20132294 (2015)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: PyTorchVideo: a deep learning library for video understanding. In: ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3478329"},{"key":"22_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/3-540-45103-X_50","volume-title":"Image Analysis","author":"G Farneb\u00e4ck","year":"2003","unstructured":"Farneb\u00e4ck, G.: Two-frame motion estimation based on polynomial expansion. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 363\u2013370. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-45103-X_50"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: IEEE\/CVF International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00630"},{"key":"22_CR12","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.neucom.2019.08.003","volume":"367","author":"N Floropoulos","year":"2019","unstructured":"Floropoulos, N., Tefas, A.: Complete vector quantization of feedforward neural networks. Neurocomputing 367, 55\u201363 (2019)","journal-title":"Neurocomputing"},{"key":"22_CR13","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural network with pruning, trained quantization and Huffman coding. In: International Conference on Learning Representations (ICLR) (2016)"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1398\u20131406 (2017)","DOI":"10.1109\/ICCV.2017.155"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Hedegaard, L., Iosifidis, A.: Continual inference: a library for efficient online inference with deep neural networks in pytorch. In: International Workshop on Computational Aspects of Deep Learning (2022)","DOI":"10.1007\/978-3-031-25082-8_2"},{"key":"22_CR16","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2015)"},{"key":"22_CR17","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. preprint, arXiv:1704.04861 abs\/1704.04861 (2017)"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"22_CR19","unstructured":"Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 29. Curran Associates, Inc. (2016)"},{"issue":"1","key":"22_CR20","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. (TPAMI) 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng, J., 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 (CVPR), pp. 4694\u20134702 (2015)","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., Schmid, C.: Action tubelet detector for spatio-temporal action localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 4415\u20134423 (2017)","DOI":"10.1109\/ICCV.2017.472"},{"key":"22_CR23","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"22_CR24","unstructured":"Karpathy, A.: CS231n convolutional neural networks for visual recognition. https:\/\/cs231n.github.io\/convolutional-networks\/. Accessed 26 Jan 2021"},{"key":"22_CR25","unstructured":"Kay, W., et al.: The kinetics human action video dataset. preprint, arXiv:1705.06950 (2017)"},{"key":"22_CR26","unstructured":"K\u00f6p\u00fckl\u00fc, O., H\u00f6rmann, S., Herzog, F., Cevikalp, H., Rigoll, G.: Dissected 3d CNNs: temporal skip connections for efficient online video processing. preprint, arXiv:2009.14639 (2020)"},{"key":"22_CR27","unstructured":"K\u00f6p\u00fckl\u00fc, O., Wei, X., Rigoll, G.: You only watch once: a unified CNN architecture for real-time spatiotemporal action localization. preprint, arXiv:1911.06644 (2019)"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"K\u00f6p\u00fckl\u00fc, O., Kose, N., Gunduz, A., Rigoll, G.: Resource efficient 3d convolutional neural networks. In: IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 1910\u20131919 (2019)","DOI":"10.1109\/ICCVW.2019.00240"},{"key":"22_CR29","unstructured":"Liu, G., et al.: Partial convolution based padding. preprint, arXiv:1811.11718, pp. 1\u201311 (2018)"},{"key":"22_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-030-01264-9_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Ma","year":"2018","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 122\u2013138. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_8"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Molchanov, P., Yang, X., Gupta, S., Kim, K., Tyree, S., Kautz, J.: Online detection and classification of dynamic hand gestures with recurrent 3d convolutional neural networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4207\u20134215 (2016)","DOI":"10.1109\/CVPR.2016.456"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Neimark, D., Bar, O., Zohar, M., Asselmann, D.: Video transformer network. In: 2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 3156\u20133165 (2021)","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Choi, S., Kim, W., Ahn, S., Kim, J., Lee, S.: Distribution padding in convolutional neural networks. In: International Conference on Image Processing (ICIP), pp. 4275\u20134279 (2019)","DOI":"10.1109\/ICIP.2019.8803537"},{"key":"22_CR34","unstructured":"van den Oord, A., et al.: WaveNet: a generative model for raw audio. preprint, arXiv:1609.03499 (2016)"},{"key":"22_CR35","unstructured":"Papers with Code: Kinetics-400 leaderboard. https:\/\/paperswithcode.com\/sota\/action-classification-on-kinetics-400. Accessed 03 Feb 2021"},{"key":"22_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/978-3-030-01252-6_17","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Passalis","year":"2018","unstructured":"Passalis, N., Tefas, A.: Learning deep representations with probabilistic knowledge transfer. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 283\u2013299. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_17"},{"issue":"3","key":"22_CR37","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. (ICCV) 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis. (ICCV)"},{"key":"22_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Singh, G., Cuzzolin, F.: Recurrent convolutions for causal 3d CNNs. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 1456\u20131465 (2019)","DOI":"10.1109\/ICCVW.2019.00183"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Singh, G., Saha, S., Sapienza, M., Torr, P., Cuzzolin, F.: Online real-time multiple spatiotemporal action localisation and prediction. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3657\u20133666 (2017)","DOI":"10.1109\/ICCV.2017.393"},{"key":"22_CR41","unstructured":"Sovrasov, V.: Ptflops, \u2018github.com\/sovrasov\/flops-counter.pytorch\u2019. MIT License. Accessed 02 Mar 2021"},{"key":"22_CR42","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: Proceedings of Machine Learning Research, vol. 97, pp. 6105\u20136114 (2019)"},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"22_CR44","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 (ICCV), pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"22_CR45","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.neucom.2018.05.083","volume":"312","author":"M Wang","year":"2018","unstructured":"Wang, M., Deng, W.: Deep visual domain adaptation: a survey. Neurocomputing 312, 135\u2013153 (2018)","journal-title":"Neurocomputing"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhu, M., Liu, Y., Lin, F., Liu, X.: DeepCache: principled cache for mobile deep vision. In: International Conference on Mobile Computing and Networking (2018)","DOI":"10.1145\/3241539.3241563"},{"key":"22_CR47","doi-asserted-by":"crossref","unstructured":"Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: Fast optimization, network minimization and transfer learning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7130\u20137138 (2017)","DOI":"10.1109\/CVPR.2017.754"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"22_CR49","doi-asserted-by":"crossref","unstructured":"Zhu, L., Sevilla-Lara, L., Yang, Y., Feiszli, M., Wang, H.: Faster recurrent networks for efficient video classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13098\u201313105 (2020)","DOI":"10.1609\/aaai.v34i07.7012"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19772-7_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T01:15:20Z","timestamp":1793150120000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-19772-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197710","9783031197727"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19772-7_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"28 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"This content has been made available to all.","name":"free","label":"Free to read"}]}}