{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T14:15:40Z","timestamp":1762956940527,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031167874"},{"type":"electronic","value":"9783031167881"}],"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\/978-3-031-16788-1_26","type":"book-chapter","created":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T20:35:56Z","timestamp":1663878956000},"page":"429-444","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Self-supervised Learning for\u00a0Unintentional Action Prediction"],"prefix":"10.1007","author":[{"given":"Olga","family":"Zatsarynna","sequence":"first","affiliation":[]},{"given":"Yazan Abu","family":"Farha","sequence":"additional","affiliation":[]},{"given":"Juergen","family":"Gall","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,20]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Ahsan, U., Madhok, R., Essa, I.: Video jigsaw: unsupervised learning of spatiotemporal context for video action recognition. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV) (2019)","DOI":"10.1109\/WACV.2019.00025"},{"key":"26_CR2","unstructured":"Bai, Y., et al.: Can temporal information help with contrastive self-supervised learning? ArXiv abs\/2011.13046 (2020)"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Behrmann, N., Fayyaz, M., Gall, J., Noroozi, M.: Long short view feature decomposition via contrastive video representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00911"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Benaim, S., et al.: Speednet: learning the speediness in videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"26_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. ArXiv abs\/2002.05709 (2020)"},{"key":"26_CR6","doi-asserted-by":"publisher","first-page":"79562","DOI":"10.1109\/ACCESS.2021.3084840","volume":"9","author":"H Cho","year":"2021","unstructured":"Cho, H., Kim, T., Chang, H.J., Hwang, W.: Self-supervised visual learning by variable playback speeds prediction of a video. IEEE Access 9, 79562\u201379571 (2021)","journal-title":"IEEE Access"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Dave, I.R., Gupta, R., Rizve, M.N., Shah, M.: TCLR: temporal contrastive learning for video representation. ArXiv abs\/2101.07974 (2021)","DOI":"10.1016\/j.cviu.2022.103406"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Diba, A., et al.: Vi2clr: video and image for visual contrastive learning of representation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00153"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Epstein, D., Chen, B., Vondrick, C.: Oops! predicting unintentional action in video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00100"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Epstein, D., Vondrick, C.: Learning goals from failure. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01104"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Feng, J.C., Hong, F.T., Zheng, W.S.: Mist: multiple instance self-training framework for video anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Fernando, B., Bilen, H., Gavves, E., Gould, S.: Self-supervised video representation learning with odd-one-out networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.607"},{"key":"26_CR13","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (2010)"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Hanson, A., Pnvr, K., Krishnagopal, S., Davis, L.S.: Bidirectional convolutional LSTM for the detection of violence in videos. In: European Conference on Computer Vision (ECCV) Workshop (2018)","DOI":"10.1007\/978-3-030-11012-3_24"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and imagenet? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Hoffmann, D., Behrmann, N., Gall, J., Brox, T., Noroozi, M.: Ranking info noise contrastive estimation: boosting contrastive learning via ranked positives. In: AAAI Conference on Artificial Intelligence (2022)","DOI":"10.1609\/aaai.v36i1.19972"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Jenni, S., Jin, H.: Time-equivariant contrastive video representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00982"},{"key":"26_CR19","unstructured":"Jing, L., Yang, X., Liu, J., Tian, Y.: Self-supervised spatiotemporal feature learning via video rotation prediction. ArXiv abs\/811.11387 (2018)"},{"key":"26_CR20","unstructured":"Kay, W., et al.: The kinetics human action video dataset. ArXiv abs\/1705.06950 (2017)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Kim, D., Cho, D., Kweon, I.S.: Self-supervised video representation learning with space-time cubic puzzles. In: AAAI Conference on Artifical Inelligence (2019)","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"26_CR22","unstructured":"Knights, J., Harwood, B., Ward, D., Vanderkop, A., Mackenzie-Ross, O., Moghadam, P.: Temporally coherent embeddings for self-supervised video representation learning. In: International Conference on Pattern Recognition (ICPR) (2020)"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Lee, H.Y., Huang, J.B., Singh, M.K., Yang, M.H.: Unsupervised representation learning by sorting sequence. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.79"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Misra, I., Zitnick, C.L., Hebert, M.: Shuffle and learn: unsupervised learning using temporal order verification. In: Proceedings of the European Conference on Computer (ECCV) (2016)","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"26_CR25","first-page":"1","volume":"32","author":"A Paszke","year":"2019","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32, 1\u201339 (2019)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Qian, R., Meng, T., Gong, B., Yang, M.H., Wang, H., Belongie, S.J., Cui, Y.: Spatiotemporal contrastive video representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Sermanet, P., et al.: Time-contrastive networks: self-supervised learning from video. In: Proceedings of International Conference in Robotics and Automation (ICRA) (2018)","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Lanz, O.: Learning to detect violent videos using convolutional long short-term memory. In: IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) (2017)","DOI":"10.1109\/AVSS.2017.8078468"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Sultani, W., Chen, C., Shah, M.: Real-world anomaly detection in surveillance videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00678"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Tian, Y., Pang, G., Chen, Y., Singh, R., Verjans, J.W., Carneiro, G.: Weakly-supervised video anomaly detection with robust temporal feature magnitude learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Shrivastava, A., Fathi, A., Guadarrama, S., Murphy, K.P.: Tracking emerges by colorizing videos. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"26_CR32","doi-asserted-by":"publisher","first-page":"3454","DOI":"10.1049\/ipr2.12258","volume":"15","author":"B Wan","year":"2021","unstructured":"Wan, B., Jiang, W., Fang, Y., Luo, Z., Ding, G.: Anomaly detection in video sequences: a benchmark and computational model. IET Image Process. 15, 3454\u20133465 (2021)","journal-title":"IET Image Process."},{"key":"26_CR33","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":"26_CR34","doi-asserted-by":"crossref","unstructured":"Wei, D., Lim, J., Zisserman, A., Freeman, W.T.: Learning and using the arrow of time. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00840"},{"key":"26_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1007\/978-3-030-58577-8_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Wu","year":"2020","unstructured":"Wu, P., et al.: Not only look, but also listen: learning multimodal violence detection under weak supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 322\u2013339. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_20"},{"key":"26_CR36","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01058"},{"key":"26_CR37","doi-asserted-by":"publisher","first-page":"3281","DOI":"10.1109\/TIP.2022.3166278","volume":"31","author":"J Xu","year":"2022","unstructured":"Xu, J., Chen, G., Lu, J., Zhou, J.: Unintentional action localization via counterfactual examples. IEEE Trans. Image Process. 31, 3281\u20133294 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Yao, T., Zhang, Y., Qiu, Z., Pan, Y., Mei, T.: Seco: exploring sequence supervision for unsupervised representation learning. In: AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i12.17274"},{"key":"26_CR39","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Zhong, J.X., Li, N., Kong, W., Liu, S., Li, T.H., Li, G.: Graph convolutional label noise cleaner: train a plug-and-play action classifier for anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00133"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, N., Chen, G., Xu, J., Zheng, W.S., Lu, J.: Temporal label aggregation for unintentional action localization. In: IEEE International Conference on Multimedia and Expo (ICME) (2021)","DOI":"10.1109\/ICME51207.2021.9428125"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16788-1_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T20:41:46Z","timestamp":1663879306000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16788-1_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031167874","9783031167881"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16788-1_26","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":"20 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"DAGM German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Konstanz","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"44","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/gcpr-vmv-2022.uni-konstanz.de\/","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":"78","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":"37","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":"47% - 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":"2.6","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}