{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:08:57Z","timestamp":1742987337789,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031159367"},{"type":"electronic","value":"9783031159374"}],"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.springer.com\/tdm"},{"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.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-15937-4_43","type":"book-chapter","created":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T08:15:35Z","timestamp":1662452135000},"page":"508-520","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Video Motion Perception for\u00a0Self-supervised Representation Learning"],"prefix":"10.1007","author":[{"given":"Wei","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dezhao","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoni","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,7]]},"reference":[{"key":"43_CR1","doi-asserted-by":"crossref","unstructured":"Benaim, S., et al.: SpeedNet: learning the speediness in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9922\u20139931 (2020)","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"43_CR2","unstructured":"Chen, P., et al.: RSPNet: relative speed perception for unsupervised video representation learning. In: AAAI. vol. 1, p. 5 (2021)"},{"key":"43_CR3","unstructured":"Cho, H., Kim, T., Chang, H.J., Hwang, W.: Self-supervised spatio-temporal representation learning using variable playback speed prediction, vol. 2, pp. 13\u201314. arXiv preprint arXiv:2003.02692 (2020)"},{"key":"43_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"43_CR5","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1422\u20131430 (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"43_CR6","first-page":"5679","volume":"33","author":"T Han","year":"2020","unstructured":"Han, T., Xie, W., Zisserman, A.: Self-supervised co-training for video representation learning. NeurIPS 33, 5679\u20135690 (2020)","journal-title":"NeurIPS"},{"key":"43_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"Jenni, S., Meishvili, G., Favaro, P.: Video representation learning by recognizing temporal transformations. In: Proceedings of the European Conference on Computer Vision, pp. 425\u2013442 (2020)","DOI":"10.1007\/978-3-030-58604-1_26"},{"key":"43_CR9","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Kim, D., Cho, D., Kweon, I.S.: Self-supervised video representation learning with space-time cubic puzzles. In: AAAI, vol. 33, pp. 8545\u20138552 (2019)","DOI":"10.1609\/aaai.v33i01.33018545"},{"issue":"3","key":"43_CR11","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1109\/TPAMI.2011.209","volume":"34","author":"O Kliper-Gross","year":"2011","unstructured":"Kliper-Gross, O., Hassner, T., et al.: The action similarity labeling challenge. IEEE Trans. Pattern Anal. Mach. Intell. 34(3), 615\u2013621 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"43_CR12","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 IEEE International Conference on Computer Vision, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"43_CR13","doi-asserted-by":"crossref","unstructured":"Luo, D., et al.: Video cloze procedure for self-supervised spatio-temporal learning. In: AAAI, pp. 11701\u201311708 (2020)","DOI":"10.1609\/aaai.v34i07.6840"},{"key":"43_CR14","doi-asserted-by":"crossref","unstructured":"Luo, D., Zhou, Y., Fang, B., Zhou, Y., Wu, D., Wang, W.: Exploring relations in untrimmed videos for self-supervised learning. ACM Trans. Multimed. Comput. Commun. App. (TOMM) 18(1s), 1\u201321 (2022)","DOI":"10.1145\/3473342"},{"key":"43_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"43_CR16","doi-asserted-by":"crossref","unstructured":"Pan, T., et al.: VideoMoCo: contrastive video representation learning with temporally adversarial examples. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11205\u201311214 (2021)","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"43_CR17","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"43_CR18","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NeurIPS, pp. 568\u2013576 (2014)"},{"key":"43_CR19","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"43_CR20","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":"43_CR21","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"43_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1007\/978-3-030-58520-4_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Wang","year":"2020","unstructured":"Wang, J., Jiao, J., Liu, Y.-H.: Self-supervised video representation learning by pace prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 504\u2013521. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_30"},{"key":"43_CR23","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Self-supervised spatio-temporal representation learning for videos by predicting motion and appearance statistics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4006\u20134015 (2019)","DOI":"10.1109\/CVPR.2019.00413"},{"key":"43_CR24","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":"43_CR25","doi-asserted-by":"crossref","unstructured":"Wei, D., Lim, J.J., Zisserman, A., Freeman, W.T.: Learning and using the arrow of time. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8052\u20138060 (2018)","DOI":"10.1109\/CVPR.2018.00840"},{"key":"43_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/978-3-030-01267-0_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Xie","year":"2018","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 318\u2013335. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_19"},{"key":"43_CR27","doi-asserted-by":"crossref","unstructured":"Xu, D., Xiao, J., Zhao, Z., Shao, J., Xie, D., Zhuang, Y.: Self-supervised spatiotemporal learning via video clip order prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10334\u201310343 (2019)","DOI":"10.1109\/CVPR.2019.01058"},{"key":"43_CR28","doi-asserted-by":"crossref","unstructured":"Yao, Y., Liu, C., Luo, D., Zhou, Y., Ye, Q.: Video playback rate perception for self-supervised spatio-temporal representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6548\u20136557 (2020)","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"43_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/978-3-030-01246-5_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 831\u2013846. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_49"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-15937-4_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T08:23:50Z","timestamp":1662452630000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-15937-4_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031159367","9783031159374"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-15937-4_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"7 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bristol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"6 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"561","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":"255","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":"4","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":"45% - 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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}