{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T15:20:22Z","timestamp":1776266422428,"version":"3.50.1"},"publisher-location":"Cham","reference-count":44,"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.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\/978-3-031-19772-7_3","type":"book-chapter","created":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T22:09:58Z","timestamp":1666908598000},"page":"36-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":42,"title":["Contrastive Positive Mining for\u00a0Unsupervised 3D Action Representation Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6895-3578","authenticated-orcid":false,"given":"Haoyuan","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1676-5505","authenticated-orcid":false,"given":"Yonghong","family":"Hou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9130-3829","authenticated-orcid":false,"given":"Wenjing","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4427-2687","authenticated-orcid":false,"given":"Wanqing","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,28]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Caetano, C., Br\u00e9mond, F., Schwartz, W.R.: Skeleton image representation for 3D action recognition based on tree structure and reference joints. In: 2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 16\u201323. IEEE (2019)","DOI":"10.1109\/SIBGRAPI.2019.00011"},{"key":"3_CR2","doi-asserted-by":"publisher","first-page":"104214","DOI":"10.1016\/j.imavis.2021.104214","volume":"112","author":"J Chen","year":"2021","unstructured":"Chen, J., Samuel, R.D.J., Poovendran, P.: LSTM with bio inspired algorithm for action recognition in sports videos. Image Vis. Comput. 112, 104214 (2021)","journal-title":"Image Vis. Comput."},{"key":"3_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"3_CR5","unstructured":"Fang, Z., Wang, J., Wang, L., Zhang, L., Yang, Y., Liu, Z.: SEED: self-supervised distillation for visual representation. arXiv preprint arXiv:2101.04731 (2021)"},{"key":"3_CR6","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. arXiv preprint arXiv:2006.07733 (2020)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Gui, L.Y., Wang, Y.X., Liang, X., Moura, J.M.: Adversarial geometry-aware human motion prediction. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 786\u2013803 (2018)","DOI":"10.1007\/978-3-030-01225-0_48"},{"key":"3_CR8","unstructured":"Gutmann, M.U., Hyv\u00e4rinen, A.: Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics. J. Mach. Learn. Res. 13(2) (2012)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"issue":"3","key":"3_CR10","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1109\/TCSVT.2016.2628339","volume":"28","author":"Y Hou","year":"2018","unstructured":"Hou, Y., Li, Z., Wang, P., Li, W.: Skeleton optical spectra-based action recognition using convolutional neural networks. IEEE Trans. Circuits Syst. Video Technol. 28(3), 807\u2013811 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: A new representation of skeleton sequences for 3D action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3288\u20133297 (2017)","DOI":"10.1109\/CVPR.2017.486"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Kundu, J.N., Gor, M., Uppala, P.K., Radhakrishnan, V.B.: Unsupervised feature learning of human actions as trajectories in pose embedding manifold. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1459\u20131467. IEEE (2019)","DOI":"10.1109\/WACV.2019.00160"},{"key":"3_CR13","unstructured":"Li, J., Wong, Y., Zhao, Q., Kankanhalli, M.S.: Unsupervised learning of view-invariant action representations. arXiv preprint arXiv:1809.01844 (2018)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Li, L., Wang, M., Ni, B., Wang, H., Yang, J., Zhang, W.: 3D human action representation learning via cross-view consistency pursuit. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4741\u20134750 (2021)","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Lin, L., Song, S., Yang, W., Liu, J.: MS2L: multi-task self-supervised learning for skeleton based action recognition. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2490\u20132498 (2020)","DOI":"10.1145\/3394171.3413548"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Liu, J., Song, S., Liu, C., Li, Y., Hu, Y.: A benchmark dataset and comparison study for multi-modal human action analytics. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 16(2), 1\u201324 (2020)","DOI":"10.1145\/3365212"},{"issue":"10","key":"3_CR17","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2019","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: NTU RGB+D 120: a large-scale benchmark for 3D human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2684\u20132701 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"3_CR18","doi-asserted-by":"publisher","first-page":"1824","DOI":"10.1109\/TCSVT.2017.2655521","volume":"28","author":"M Liu","year":"2017","unstructured":"Liu, M., Liu, H., Chen, C.: 3D action recognition using multiscale energy-based global ternary image. IEEE Trans. Circuits Syst. Video Technol. 28(8), 1824\u20131838 (2017)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3_CR19","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Luo, Z., Peng, B., Huang, D.A., Alahi, A., Fei-Fei, L.: Unsupervised learning of long-term motion dynamics for videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2203\u20132212 (2017)","DOI":"10.1109\/CVPR.2017.751"},{"key":"3_CR21","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"3_CR22","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":"3_CR23","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"3_CR24","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.ins.2021.04.023","volume":"569","author":"H Rao","year":"2021","unstructured":"Rao, H., Xu, S., Hu, X., Cheng, J., Hu, B.: Augmented skeleton based contrastive action learning with momentum LSTM for unsupervised action recognition. Inf. Sci. 569, 90\u2013109 (2021)","journal-title":"Inf. Sci."},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+D: a large scale dataset for 3D human activity analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Shi, Z., Kim, T.K.: Learning and refining of privileged information-based RNNs for action recognition from depth sequences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3461\u20133470 (2017)","DOI":"10.1109\/CVPR.2017.498"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Si, C., Chen, W., Wang, W., Wang, L., Tan, T.: An attention enhanced graph convolutional LSTM network for skeleton-based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1227\u20131236 (2019)","DOI":"10.1109\/CVPR.2019.00132"},{"issue":"7","key":"3_CR28","doi-asserted-by":"publisher","first-page":"3459","DOI":"10.1109\/TIP.2018.2818328","volume":"27","author":"S Song","year":"2018","unstructured":"Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: Spatio-temporal attention-based LSTM networks for 3D action recognition and detection. IEEE Trans. Image Process. 27(7), 3459\u20133471 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"3_CR29","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: International Conference on Machine Learning, pp. 843\u2013852. PMLR (2015)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Su, K., Liu, X., Shlizerman, E.: Predict & cluster: unsupervised skeleton based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9631\u20139640 (2020)","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"3_CR31","doi-asserted-by":"publisher","first-page":"104141","DOI":"10.1016\/j.imavis.2021.104141","volume":"109","author":"N Sun","year":"2021","unstructured":"Sun, N., Leng, L., Liu, J., Han, G.: Multi-stream slowfast graph convolutional networks for skeleton-based action recognition. Image Vis. Comput. 109, 104141 (2021)","journal-title":"Image Vis. Comput."},{"key":"3_CR32","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. arXiv preprint arXiv:1703.01780 (2017)"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Thoker, F.M., Doughty, H., Snoek, C.G.: Skeleton-contrastive 3D action representation learning. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1655\u20131663 (2021)","DOI":"10.1145\/3474085.3475307"},{"key":"3_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-030-58621-8_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 776\u2013794. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_45"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Wang, P., Li, W., Gao, Z., Zhang, Y., Tang, C., Ogunbona, P.: Scene flow to action map: a new representation for RGB-D based action recognition with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 595\u2013604 (2017)","DOI":"10.1109\/CVPR.2017.52"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Wei, C., et al.: Iterative reorganization with weak spatial constraints: solving arbitrary jigsaw puzzles for unsupervised representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1910\u20131919 (2019)","DOI":"10.1109\/CVPR.2019.00201"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3733\u20133742 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"3_CR38","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.ins.2018.12.050","volume":"480","author":"Y Xiao","year":"2019","unstructured":"Xiao, Y., Chen, J., Wang, Y., Cao, Z., Zhou, J.T., Bai, X.: Action recognition for depth video using multi-view dynamic images. Inf. Sci. 480, 287\u2013304 (2019)","journal-title":"Inf. Sci."},{"key":"3_CR39","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"3_CR40","unstructured":"You, Y., Gitman, I., Ginsburg, B.: Large batch training of convolutional networks. arXiv preprint arXiv:1708.03888 (2017)"},{"key":"3_CR41","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: self-supervised learning via redundancy reduction. arXiv preprint arXiv:2103.03230 (2021)"},{"key":"3_CR42","doi-asserted-by":"publisher","first-page":"102942","DOI":"10.1016\/j.jvcir.2020.102942","volume":"73","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Hou, Y., Wang, P., Guo, Z., Li, W.: SAR-NAS: skeleton-based action recognition via neural architecture searching. J. Vis. Commun. Image Represent. 73, 102942 (2020)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, X., Xu, C., Tao, D.: Context aware graph convolution for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14333\u201314342 (2020)","DOI":"10.1109\/CVPR42600.2020.01434"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Zheng, N., Wen, J., Liu, R., Long, L., Dai, J., Gong, Z.: Unsupervised representation learning with long-term dynamics for skeleton based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11853"}],"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_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:48:36Z","timestamp":1710262116000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19772-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197710","9783031197727"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19772-7_3","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)"}}]}}