{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T18:19:20Z","timestamp":1771265960991,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T00:00:00Z","timestamp":1738800000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T00:00:00Z","timestamp":1738800000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42394060 and 42394064"],"award-info":[{"award-number":["42394060 and 42394064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42394060 and 42394064"],"award-info":[{"award-number":["42394060 and 42394064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42394060 and 42394064"],"award-info":[{"award-number":["42394060 and 42394064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42394060 and 42394064"],"award-info":[{"award-number":["42394060 and 42394064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42394060 and 42394064"],"award-info":[{"award-number":["42394060 and 42394064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42394060 and 42394064"],"award-info":[{"award-number":["42394060 and 42394064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42394060 and 42394064"],"award-info":[{"award-number":["42394060 and 42394064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s10994-024-06667-z","type":"journal-article","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T15:38:56Z","timestamp":1738856336000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Progressive semantic learning for unsupervised skeleton-based action recognition"],"prefix":"10.1007","volume":"114","author":[{"given":"Hao","family":"Qin","sequence":"first","affiliation":[]},{"given":"Luyuan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Kong","sequence":"additional","affiliation":[]},{"given":"Zhuoran","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Xianzhou","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Mengxu","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Qiang","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,6]]},"reference":[{"key":"6667_CR1","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: Vicreg: Variance-invariance-covariance regularization for self-supervised learning. arXiv preprint arXiv:2105.04906 (2021)"},{"key":"6667_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"6667_CR3","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020). Unsupervised learning of visual features by contrasting cluster assignments. Advances in neural information processing systems, 33, 9912\u20139924.","journal-title":"Advances in neural information processing systems"},{"key":"6667_CR4","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 (2020). PMLR"},{"key":"6667_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhao, L., Yuan, J., Tian, Y., Xia, Z., Geng, S., Han, L., Metaxas, D.N.: Hierarchically self-supervised transformer for human skeleton representation learning. In: European Conference on Computer Vision, pp. 185\u2013202 (2022). Springer","DOI":"10.1007\/978-3-031-19809-0_11"},{"issue":"1","key":"6667_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the em algorithm. Journal of the royal statistical society: series B (methodological), 39(1), 1\u201322.","journal-title":"Journal of the royal statistical society: series B (methodological)"},{"key":"6667_CR7","doi-asserted-by":"crossref","unstructured":"Dong, J., Sun, S., Liu, Z., Chen, S., Liu, B., Wang, X.: Hierarchical contrast for unsupervised skeleton-based action representation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 525\u2013533 (2023)","DOI":"10.1609\/aaai.v37i1.25127"},{"key":"6667_CR8","first-page":"21271","volume":"33","author":"J-B Grill","year":"2020","unstructured":"Grill, J.-B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Avila Pires, B., Guo, Z., Gheshlaghi Azar, M., et al. (2020). Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, 33, 21271\u201321284.","journal-title":"Advances in neural information processing systems"},{"key":"6667_CR9","doi-asserted-by":"crossref","unstructured":"Guo, T., Liu, H., Chen, Z., Liu, M., Wang, T., Ding, R.: Contrastive learning from extremely augmented skeleton sequences for self-supervised action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 762\u2013770 (2022)","DOI":"10.1609\/aaai.v36i1.19957"},{"key":"6667_CR10","doi-asserted-by":"crossref","unstructured":"Guo, Y., Xu, M., Li, J., Ni, B., Zhu, X., Sun, Z., Xu, Y.: Hcsc: Hierarchical contrastive selective coding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9706\u20139715 (2022)","DOI":"10.1109\/CVPR52688.2022.00948"},{"key":"6667_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"6667_CR12","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"},{"key":"6667_CR13","doi-asserted-by":"crossref","unstructured":"Hershey, J.R., Olsen, P.A.: Approximating the kullback leibler divergence between gaussian mixture models. In: 2007 IEEE International Conference on Acoustics, Speech and Signal Processing-ICASSP\u201907, vol. 4, p. 317 (2007). IEEE","DOI":"10.1109\/ICASSP.2007.366913"},{"key":"6667_CR14","doi-asserted-by":"crossref","unstructured":"Hua, Y., Wu, W., Zheng, C., Lu, A., Liu, M., Chen, C., Wu, S.: Part aware contrastive learning for self-supervised action recognition. arXiv preprint arXiv:2305.00666 (2023)","DOI":"10.24963\/ijcai.2023\/95"},{"key":"6667_CR15","doi-asserted-by":"crossref","unstructured":"Kim, B., Chang, H.J., Kim, J., Choi, J.Y.: Global-local motion transformer for unsupervised skeleton-based action learning. In: European Conference on Computer Vision, pp. 209\u2013225 (2022). Springer","DOI":"10.1007\/978-3-031-19772-7_13"},{"key":"6667_CR16","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":"6667_CR17","unstructured":"Li, J., Zhou, P., Xiong, C., Hoi, S.C.: Prototypical contrastive learning of unsupervised representations. arXiv preprint arXiv:2005.04966 (2020)"},{"key":"6667_CR18","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":"6667_CR19","doi-asserted-by":"crossref","unstructured":"Lin, L., Zhang, J., Liu, J.: Actionlet-dependent contrastive learning for unsupervised skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2363\u20132372 (2023)","DOI":"10.1109\/CVPR52729.2023.00234"},{"key":"6667_CR20","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 Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16(2), 1\u201324 (2020)","DOI":"10.1145\/3365212"},{"issue":"10","key":"6667_CR21","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. (2019). Ntu rgb+ d 120: A large-scale benchmark for 3d human activity understanding. IEEE transactions on pattern analysis and machine intelligence, 42(10), 2684\u20132701.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"6667_CR22","unstructured":"Maaten, L., Hinton, G.: Visualizing data using t-sne. Journal of machine learning research 9(11) (2008)"},{"key":"6667_CR23","unstructured":"MacQueen, J., et\u00a0al.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, vol.1, pp. 281\u2013297 (1967). Oakland, CA, USA"},{"key":"6667_CR24","doi-asserted-by":"crossref","unstructured":"Mao, Y., Zhou, W., Lu, Z., Deng, J., Li, H.: Cmd: Self-supervised 3d action representation learning with cross-modal mutual distillation. In: European Conference on Computer Vision, pp. 734\u2013752 (2022). Springer","DOI":"10.1007\/978-3-031-20062-5_42"},{"key":"6667_CR25","doi-asserted-by":"crossref","unstructured":"Noroozi, M., Vinjimoor, A., Favaro, P., Pirsiavash, H.: Boosting self-supervised learning via knowledge transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9359\u20139367 (2018)","DOI":"10.1109\/CVPR.2018.00975"},{"key":"6667_CR26","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"6667_CR27","doi-asserted-by":"crossref","unstructured":"Peng, W., Hong, X., Chen, H., Zhao, G.: Learning graph convolutional network for skeleton-based human action recognition by neural searching. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 2669\u20132676 (2020)","DOI":"10.1609\/aaai.v34i03.5652"},{"key":"6667_CR28","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. (2021). Augmented skeleton based contrastive action learning with momentum lstm for unsupervised action recognition. Information Sciences, 569, 90\u2013109.","journal-title":"Information Sciences"},{"key":"6667_CR29","doi-asserted-by":"crossref","unstructured":"Shah, A., Roy, A., Shah, K., Mishra, S., Jacobs, D., Cherian, A., Chellappa, R.: Halp: Hallucinating latent positives for skeleton-based self-supervised learning of actions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18846\u201318856 (2023)","DOI":"10.1109\/CVPR52729.2023.01807"},{"key":"6667_CR30","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":"6667_CR31","doi-asserted-by":"crossref","unstructured":"Su, Y., Lin, G., Wu, Q.: Self-supervised 3d skeleton action representation learning with motion consistency and continuity. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13328\u201313338 (2021)","DOI":"10.1109\/ICCV48922.2021.01308"},{"key":"6667_CR32","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":"6667_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":"6667_CR34","unstructured":"Wang, T., Isola, P.: Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: International Conference on Machine Learning, pp. 9929\u20139939 (2020). PMLR"},{"key":"6667_CR35","doi-asserted-by":"crossref","unstructured":"Wang, F., Liu, H.: Understanding the behaviour of contrastive loss. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2495\u20132504 (2021)","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"6667_CR36","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":"6667_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-007-0114-2","volume":"14","author":"X Wu","year":"2008","unstructured":"Wu, X., Kumar, V., Ross Quinlan, J., Ghosh, J., Yang, Q., Motoda, H., McLachlan, G. J., Ng, A., Liu, B., Yu, P. S., et al. (2008). Top 10 algorithms in data mining. Knowledge and information systems, 14, 1\u201337.","journal-title":"Knowledge and information systems"},{"key":"6667_CR38","doi-asserted-by":"crossref","unstructured":"Yang, S., Liu, J., Lu, S., Er, M.H., Kot, A.C.: Skeleton cloud colorization for unsupervised 3d action representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13423\u201313433 (2021)","DOI":"10.1109\/ICCV48922.2021.01317"},{"key":"6667_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hou, Y., Zhang, W., Li, W.: Contrastive positive mining for unsupervised 3d action representation learning. In: European Conference on Computer Vision, pp. 36\u201351 (2022). Springer","DOI":"10.1007\/978-3-031-19772-7_3"},{"key":"6667_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lin, L., Liu, J.: Hierarchical consistent contrastive learning for skeleton-based action recognition with growing augmentations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 3427\u20133435 (2023)","DOI":"10.1609\/aaai.v37i3.25451"},{"key":"6667_CR41","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"},{"key":"6667_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Duan, H., Rao, A., Su, B., Wang, J.: Self-supervised action representation learning from partial spatio-temporal skeleton sequences. arXiv preprint arXiv:2302.09018 (2023)","DOI":"10.1609\/aaai.v37i3.25495"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-024-06667-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-024-06667-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-024-06667-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T01:02:33Z","timestamp":1770339753000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-024-06667-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,6]]},"references-count":42,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["6667"],"URL":"https:\/\/doi.org\/10.1007\/s10994-024-06667-z","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,6]]},"assertion":[{"value":"7 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 August 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"None.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}],"article-number":"64"}}