{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T16:43:12Z","timestamp":1785602592929,"version":"3.56.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030697556","type":"print"},{"value":"9783030697563","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","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":[[2021]]},"DOI":"10.1007\/978-3-030-69756-3_13","type":"book-chapter","created":{"date-parts":[[2021,2,23]],"date-time":"2021-02-23T08:03:17Z","timestamp":1614067397000},"page":"184-198","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Real-Time Spatio-Temporal Action Localization via Learning Motion Representation"],"prefix":"10.1007","author":[{"given":"Yuanzhong","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhigang","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyu","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianqing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,24]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gao, J., Nevatia, R.: Spatio-temporal action detection with cascade proposal and location anticipation. arXiv preprint arXiv:1708.00042 (2017)","DOI":"10.5244\/C.31.95"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"He, J., Deng, Z., Ibrahim, M.S., Mori, G.: Generic tubelet proposals for action localization. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 343\u2013351. IEEE (2018)","DOI":"10.1109\/WACV.2018.00044"},{"key":"13_CR3","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1016\/j.jvcir.2018.12.019","volume":"58","author":"Y Ye","year":"2019","unstructured":"Ye, Y., Yang, X., Tian, Y.: Discovering spatio-temporal action tubes. J. Visual Commun. Image Represent. 58, 515\u2013524 (2019)","journal-title":"J. Visual Commun. Image Represent."},{"key":"13_CR4","unstructured":"K\u00f6p\u00fckl\u00fc, O., Wei, X., Rigoll, G.: You only watch once: a unified CNN architecture for real-time spatiotemporal action localization. arXiv preprint arXiv:1911.06644 (2019)"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Yang, X., Yang, X., Liu, M.Y., Xiao, F., Davis, L.S., Kautz, J.: Step: spatio-temporal progressive learning for video action detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 264\u2013272 (2019)","DOI":"10.1109\/CVPR.2019.00035"},{"key":"13_CR6","doi-asserted-by":"publisher","first-page":"107312","DOI":"10.1016\/j.patcog.2020.107312","volume":"103","author":"D Zhang","year":"2020","unstructured":"Zhang, D., He, L., Tu, Z., Zhang, S., Han, F., Yang, B.: Learning motion representation for real-time spatio-temporal action localization. Pattern Recognit. 103, 107312 (2020)","journal-title":"Pattern Recognit."},{"key":"13_CR7","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: A dataset of 101 human action classes from videos in the wild. Center Res. Comput. Vis. 2 (2012)"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: International Conference on Computer Vision (ICCV), pp. 3192\u20133199 (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: Ava: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6047\u20136056 (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"13_CR12","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"13_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"13_CR15","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, 2961\u20132969 (2017)"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"13_CR17","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Singh, G., Saha, S., Sapienza, M., Torr, P.H., Cuzzolin, F.: Online real-time multiple spatiotemporal action localisation and prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3637\u20133646 (2017)","DOI":"10.1109\/ICCV.2017.393"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Learning to track for spatio-temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3164\u20133172 (2015)","DOI":"10.1109\/ICCV.2015.362"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Klaser, A., Marsza\u0142ek, M., Schmid, C.: A spatio-temporal descriptor based on 3D-gradients (2008)","DOI":"10.5244\/C.22.99"},{"key":"13_CR21","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Crasto, N., Weinzaepfel, P., Alahari, K., Schmid, C.: Mars: motion-augmented RGB stream for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7882\u20137891 (2019)","DOI":"10.1109\/CVPR.2019.00807"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-net: CNNs for optical flow using pyramid, warping, and cost volume. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8934\u20138943 (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 284\u2013293 (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"13_CR28","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: STAT, vol. 9, p. 1050 (2015)"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Teed, Z., Deng, J.: Raft: recurrent all-pairs field transforms for optical flow. arXiv preprint arXiv:2003.12039 (2020)","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: Flownet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Hui, T.W., Tang, X., Change Loy, C.: Liteflownet: a lightweight convolutional neural network for optical flow estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8981\u20138989 (2018)","DOI":"10.1109\/CVPR.2018.00936"},{"key":"13_CR33","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":"13_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, C., Zou, Y., Chen, G., Gan, L.: Pan: towards fast action recognition via learning persistence of appearance. arXiv preprint arXiv:2008.03462 (2020)","DOI":"10.1145\/3343031.3350876"},{"key":"13_CR35","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: Proceedings of the International Conference on Computer Vision (ICCV) (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"13_CR36","unstructured":"Duarte, K., Rawat, Y., Shah, M.: Videocapsulenet: a simplified network for action detection. In: Advances in Neural Information Processing Systems, pp. 7610\u20137619 (2018)"},{"key":"13_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-319-46493-0_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Peng","year":"2016","unstructured":"Peng, X., Schmid, C.: Multi-region two-stream R-CNN for action detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 744\u2013759. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_45"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Saha, S., Singh, G., Sapienza, M., Torr, P.H., Cuzzolin, F.: Deep learning for detecting multiple space-time action tubes in videos. Pattern Recognit. (2015)","DOI":"10.5244\/C.30.58"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Hou, R., Chen, C., Shah, M.: Tube convolutional neural network (T-CNN) for action detection in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5822\u20135831 (2017)","DOI":"10.1109\/ICCV.2017.620"},{"key":"13_CR40","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., Schmid, C.: Action tubelet detector for spatio-temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision, 4405\u20134413 (2017)"},{"key":"13_CR41","unstructured":"Alwando, E.H.P., Chen, Y.T., Fang, W.H.: CNN-based multiple path search for action tube detection in videos. IEEE Trans. Circ. Syst. Video Technol. 30(1), 104\u2013116 (2018)"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, H., Yi, Y., Li, Q., Huang, D.: P3D-CTN: pseudo-3D convolutional tube network for spatio-temporal action detection in videos. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 300\u2013304. IEEE (2019)","DOI":"10.1109\/ICIP.2019.8802979"},{"key":"13_CR43","doi-asserted-by":"crossref","unstructured":"Singh, G., Saha, S., Cuzzolin, F.: Predicting action tubes. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-11015-4_11"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020 Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69756-3_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,23]],"date-time":"2021-02-23T08:14:39Z","timestamp":1614068079000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69756-3_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030697556","9783030697563"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69756-3_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"24 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","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":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"33% - 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":"3","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":"The conference was held virtually.","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)"}}]}}