{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T00:01:20Z","timestamp":1792454480873,"version":"4.5.0"},"reference-count":117,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62172020"],"award-info":[{"award-number":["62172020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s11263-025-02644-8","type":"journal-article","created":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T03:45:13Z","timestamp":1767757513000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond"],"prefix":"10.1007","volume":"134","author":[{"given":"Jiahang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lilang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0468-9576","authenticated-orcid":false,"given":"Jiaying","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,7]]},"reference":[{"key":"2644_CR1","doi-asserted-by":"crossref","unstructured":"Assran, M., Duval, Q., Misra, I., Bojanowski, P., Vincent, P., Rabbat, M., LeCun, Y., & Ballas, N. (2023). Self-supervised learning from images with a joint-embedding predictive architecture. In IEEE CVPR, 15619\u201315629.","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"2644_CR2","doi-asserted-by":"crossref","unstructured":"Bai, Y., Yang, Y., Zhang, W., & Mei, T. (2022). Directional self-supervised learning for heavy image augmentations. In IEEE CVPR.","DOI":"10.1109\/CVPR52688.2022.01619"},{"key":"2644_CR3","unstructured":"Bardes, A., Garrido, Q., Ponce, J., Chen, X., Rabbat, M., LeCun, Y., Assran, M., & Ballas, N. (2024). Revisiting feature prediction for learning visual representations from video. arXiv:2404.08471."},{"key":"2644_CR4","unstructured":"Bardes, A., Ponce, J., & LeCun, Y. (2021). Vicreg: Variance-invariance-covariance regularization for self-supervised learning. arXiv:2105.04906"},{"key":"2644_CR5","unstructured":"Bian, C., Feng, W., Meng, F., & Wang, S. (2022). View-invariant skeleton-based action recognition via global-local contrastive learning. arXiv:2209.11634"},{"issue":"2","key":"2644_CR6","doi-asserted-by":"publisher","first-page":"34","DOI":"10.3390\/brainsci9020034","volume":"9","author":"C Buckley","year":"2019","unstructured":"Buckley, C., Alcock, L., McArdle, R., Rehman, R. Z. U., Del Din, S., Mazz\u00e0, C., Yarnall, A. J., & Rochester, L. (2019). The role of movement analysis in diagnosing and monitoring neurodegenerative conditions: Insights from gait and postural control. Brain sciences, 9(2), 34.","journal-title":"Brain sciences"},{"issue":"10","key":"2644_CR7","doi-asserted-by":"publisher","first-page":"6131","DOI":"10.1109\/TITS.2020.3006768","volume":"22","author":"F Camara","year":"2020","unstructured":"Camara, F., Bellotto, N., Cosar, S., Nathanael, D., Althoff, M., Wu, J., Ruenz, J., Dietrich, A., & Fox, C. W. (2020). Pedestrian models for autonomous driving part i: low-level models, from sensing to tracking. IEEE Transactions on Intelligent Transportation Systems, 22(10), 6131\u20136151.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"2644_CR8","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.-E., & Sheikh, Y. (2017). Realtime multi-person 2d pose estimation using part affinity fields. In IEEE CVPR.","DOI":"10.1109\/CVPR.2017.143"},{"key":"2644_CR9","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., & Douze, M. (2018). Deep clustering for unsupervised learning of visual features. In ECCV, pages 132\u2013149.","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"2644_CR10","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020). Unsupervised learning of visual features by contrasting cluster assignments. NeurIPS, pages 9912\u20139924."},{"key":"2644_CR11","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In ICCV, pages 9650\u20139660.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2644_CR12","first-page":"6061","volume":"32","author":"J Chen","year":"2023","unstructured":"Chen, J., Jin, Z., Wang, Q., & Meng, H. (2023). Self-supervised 3D behavior representation learning based on homotopic hyperbolic embedding. IEEE TIP, 32, 6061\u20136074.","journal-title":"IEEE TIP"},{"key":"2644_CR13","unstructured":"Chen T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In ICML."},{"key":"2644_CR14","unstructured":"Chen, T.S., Hung, W.-C., Tseng, H.-Y., Chien, S.-Y., & Yang, M.-H. (2021). Incremental false negative detection for contrastive learning. arXiv:2106.03719"},{"key":"2644_CR15","doi-asserted-by":"crossref","unstructured":"Chen, X., & He, K. (2021). Exploring simple siamese representation learning. In IEEE CVPR.","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"2644_CR16","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhao, L., Yuan, J., Tian, Y., Xia, Z., Geng, S., Han, L., & Metaxas, D.N. (2022). Hierarchically self-supervised transformer for human skeleton representation learning. In ECCV.","DOI":"10.1007\/978-3-031-19809-0_11"},{"key":"2644_CR17","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., & Hu, W. (2021). Channel-wise topology refinement graph convolution for skeleton-based action recognition. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"2644_CR18","doi-asserted-by":"crossref","unstructured":"Cheng, K., Zhang, Y., He, X., Chen, W., Cheng, J., & Lu, H. (2020). Skeleton-based action recognition with shift graph convolutional network. In IEEE CVPR.","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"2644_CR19","doi-asserted-by":"crossref","unstructured":"Cheng, Y.-B., Chen, X., Chen, J., Wei, P., & Zhang, D. (2021). and Liang Lin. Hierarchical transformer: Unsupervised representation learning for skeleton-based human action recognition. In IEEE ICME.","DOI":"10.1109\/ICME51207.2021.9428459"},{"key":"2644_CR20","unstructured":"Darcet, T., Oquab, M., Mairal, J., & Bojanowski, P. (2023). Vision transformers need registers. arXiv:2309.16588."},{"issue":"9","key":"2644_CR21","doi-asserted-by":"publisher","first-page":"952","DOI":"10.1016\/j.medengphy.2016.06.015","volume":"38","author":"E Dolatabadi","year":"2016","unstructured":"Dolatabadi, E., Taati, B., & Mihailidis, A. (2016). Concurrent validity of the microsoft kinect for windows v2 for measuring spatiotemporal gait parameters. Medical engineering & physics, 38(9), 952\u2013958.","journal-title":"Medical engineering & physics"},{"key":"2644_CR22","doi-asserted-by":"crossref","unstructured":"Dong, J., Sun, S., Liu, Z., Chen, S., Liu, B., & Wang, X. (2023). Hierarchical contrast for unsupervised skeleton-based action representation learning. In AAAI.","DOI":"10.1609\/aaai.v37i1.25127"},{"key":"2644_CR23","unstructured":"Franco, L., Mandica, P., Munjal, B., & Galasso, F. (2023). Hyperbolic self-paced learning for self-supervised skeleton-based action representations. In ICLR."},{"key":"2644_CR24","unstructured":"Ganin, Y., & Lempitsky, V. (2015). Unsupervised domain adaptation by backpropagation. In ICML, pages 1180\u20131189."},{"key":"2644_CR25","doi-asserted-by":"crossref","unstructured":"Gao, L., Ji, Y., Yang, Y., & Shen, H. (2022). Global-local cross-view fisher discrimination for view-invariant action recognition. In ACM MM.","DOI":"10.1145\/3503161.3548280"},{"issue":"5","key":"2644_CR26","doi-asserted-by":"publisher","first-page":"1546","DOI":"10.1007\/s11263-023-01898-4","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao, P., Lin, Z., Zhang, R., Fang, R., Li, H., Li, H., & Qiao, Yu. (2024). Mimic before reconstruct: Enhancing masked autoencoders with feature mimicking. IJCV, 132(5), 1546\u20131556.","journal-title":"IJCV"},{"key":"2644_CR27","unstructured":"Gao, X., Yang, Y., Zhang, Y., Li, M., Yu, J.-G., & Du, S. (2021). Efficient spatio-temporal contrastive learning for skeleton-based 3d action recognition. IEEE TMM."},{"key":"2644_CR28","unstructured":"Gidaris, S., Singh, P., & Komodakis, N. (2018). Unsupervised representation learning by predicting image rotations. arXiv:1803.07728"},{"key":"2644_CR29","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. NeurIPS, 33, 21271\u201321284.","journal-title":"NeurIPS"},{"key":"2644_CR30","unstructured":"Gui, J., Chen, T., Cao, Q., Sun, Z., Luo, H., & Tao, D. (2023). A survey of self-supervised learning from multiple perspectives: Algorithms, theory, applications and future trends. arXiv:2301.05712"},{"key":"2644_CR31","doi-asserted-by":"crossref","unstructured":"Guo, T., Liu, H., Chen, Z., Liu, M., Wang, T., & Ding, R. (2022). Contrastive learning from extremely augmented skeleton sequences for self-supervised action recognition. In AAAI.","DOI":"10.1609\/aaai.v36i1.19957"},{"key":"2644_CR32","unstructured":"Haghighat, M., Moghadam, P., Mohamed, S., & Koniusz, P. Pre-training with random orthogonal projection image modeling. arXiv:2310.18737"},{"key":"2644_CR33","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In IEEE CVPR.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2644_CR34","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In IEEE CVPR.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2644_CR35","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. NeurIPS."},{"key":"2644_CR36","doi-asserted-by":"crossref","unstructured":"Hua, Y., Wu, W., Zheng, C., Lu, A., Liu, M., Chen, C., & Wu, S. (2023). Part aware contrastive learning for self-supervised action recognition. arXiv:2305.00666","DOI":"10.24963\/ijcai.2023\/95"},{"key":"2644_CR37","doi-asserted-by":"crossref","unstructured":"Huynh, T., Kornblith, S., Walter, M.R., Maire, M., & Khademi, M. (2022). Boosting contrastive self-supervised learning with false negative cancellation. In IEEE WACV, pages 2785\u20132795.","DOI":"10.1109\/WACV51458.2022.00106"},{"key":"2644_CR38","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., & Sminchisescu, C. (2013). Human3. 6m: Large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE TPAMI, 36(7):1325\u20131339.","DOI":"10.1109\/TPAMI.2013.248"},{"key":"2644_CR39","unstructured":"Jing, L., Vincent, P., LeCun, Y., & Tian, Y. (2022). Understanding dimensional collapse in contrastive self-supervised learning. In ICLR."},{"key":"2644_CR40","volume-title":"Hyung Jin Chang, Jungho Kim, and Jin Young Choi","author":"B Kim","year":"2022","unstructured":"Kim, B. (2022). Hyung Jin Chang, Jungho Kim, and Jin Young Choi. ECCV: Global-local motion transformer for unsupervised skeleton-based action learning."},{"key":"2644_CR41","doi-asserted-by":"crossref","unstructured":"Lee, H.-Y., Huang, J.-B., Singh, M., & Yang, M.-H. (2017). Unsupervised representation learning by sorting sequences. In ICCV.","DOI":"10.1109\/ICCV.2017.79"},{"key":"2644_CR42","doi-asserted-by":"crossref","unstructured":"Lee, J., Lee, M., Lee, D., & Lee, S. (2023). Hierarchically decomposed graph convolutional networks for skeleton-based action recognition. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00958"},{"issue":"10","key":"2644_CR43","doi-asserted-by":"publisher","first-page":"2886","DOI":"10.3390\/s20102886","volume":"20","author":"J Lee","year":"2020","unstructured":"Lee, J., & Ahn, B. (2020). Real-time human action recognition with a low-cost rgb camera and mobile robot platform. Sensors, 20(10), 2886.","journal-title":"Sensors"},{"key":"2644_CR44","unstructured":"Li, J., Wong, Y., Zhao, Q., & Kankanhalli, M.S. (2018). Unsupervised learning of view-invariant action representations. NeurIPS."},{"key":"2644_CR45","unstructured":"Li, J., Zhou, P., Xiong, C., & Hoi, S.C.H. (2020). Prototypical contrastive learning of unsupervised representations. arXiv:2005.04966, 2020."},{"key":"2644_CR46","doi-asserted-by":"crossref","unstructured":"Li, L., Wang, M., Ni, B., Wang, H., Yang, J., & Zhang, W. (2021). 3D human action representation learning via cross-view consistency pursuit. In IEEE CVPR.","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"2644_CR47","doi-asserted-by":"crossref","unstructured":"Li, W., Xie, J., & Loy, C.C. (2023). Correlational image modeling for self-supervised visual pre-training. In IEEE CVPR, pages 15105\u201315115.","DOI":"10.1109\/CVPR52729.2023.01450"},{"key":"2644_CR48","doi-asserted-by":"crossref","unstructured":"Lin, L., Song, S., Yang, W., & Liu, J. (2020). Ms2l: Multi-task self-supervised learning for skeleton based action recognition. In ACM MM.","DOI":"10.1145\/3394171.3413548"},{"key":"2644_CR49","doi-asserted-by":"crossref","unstructured":"Lin, L., Wu, L., Zhang, J., & Liu, J. (2024). Idempotent unsupervised representation learning for skeleton-based action recognition. In ECCV, pages 75\u201392.","DOI":"10.1007\/978-3-031-73347-5_5"},{"key":"2644_CR50","doi-asserted-by":"crossref","unstructured":"Lin, L., Zhang, J., & Liu, J. (2023). Actionlet-dependent contrastive learning for unsupervised skeleton-based action recognition. In IEEE CVPR.","DOI":"10.1109\/CVPR52729.2023.00234"},{"key":"2644_CR51","doi-asserted-by":"crossref","unstructured":"Lin, L., Zhang, J., & Liu, J. (2024). Mutual information driven equivariant contrastive learning for 3d action representation learning. IEEE TIP.","DOI":"10.1109\/TIP.2024.3372451"},{"key":"2644_CR52","doi-asserted-by":"crossref","unstructured":"Liu, J., Song, S., Liu, C., Li, Y., & Hu, Y. (2020). A benchmark dataset and comparison study for multi-modal human action analytics. ACM TOMM, 16(2):41:1\u201341:24.","DOI":"10.1145\/3365212"},{"issue":"10","key":"2644_CR53","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 TPAMI, 42(10), 2684\u20132701.","journal-title":"IEEE TPAMI"},{"key":"2644_CR54","doi-asserted-by":"crossref","unstructured":"Liu, W., Qian Bao, Yu, S., & Mei, T. (2022). Recent advances of monocular 2d and 3D human pose estimation: a deep learning perspective. ACM Computing Surveys, 55(4), 1\u201341.","DOI":"10.1145\/3524497"},{"issue":"12","key":"2644_CR55","doi-asserted-by":"publisher","first-page":"155014771989453","DOI":"10.1177\/1550147719894532","volume":"15","author":"IH Lopez-Nava","year":"2019","unstructured":"Lopez-Nava, I. H., & Mu\u00f1oz-Mel\u00e9ndez, A. (2019). Human action recognition based on low-and high-level data from wearable inertial sensors. International Journal of Distributed Sensor Networks, 15(12), 1550147719894532.","journal-title":"International Journal of Distributed Sensor Networks"},{"key":"2644_CR56","doi-asserted-by":"crossref","unstructured":"Lu, Y., Wen, L., Liu, J., Liu, Y., & Tian, X. (2022). Self-supervision can be a good few-shot learner. In ECCV.","DOI":"10.1007\/978-3-031-19800-7_43"},{"key":"2644_CR57","volume-title":"Juan Carlos Niebles, and Li Fei-Fei","author":"Z Luo","year":"2018","unstructured":"Luo, Z., Hsieh, J.-T., & Jiang, L. (2018). Juan Carlos Niebles, and Li Fei-Fei. In ECCV: Graph distillation for action detection with privileged modalities."},{"key":"2644_CR58","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/j.neucom.2022.02.045","volume":"489","author":"K Lyu","year":"2022","unstructured":"Lyu, K., Chen, H., Liu, Z., Zhang, B., & Wang, R. (2022). 3D human motion prediction: A survey. Neurocomputing, 489, 345\u2013365.","journal-title":"Neurocomputing"},{"key":"2644_CR59","doi-asserted-by":"crossref","unstructured":"Mao, Y., Deng, J., Zhou, W., Fang, Y., Ouyang, W., & Li, H. (2023). Masked motion predictors are strong 3d action representation learners. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00934"},{"key":"2644_CR60","doi-asserted-by":"crossref","unstructured":"Mao, Y., Zhou, W., Lu, Z., Deng, J., & Li, H. (2022). CMD: Self-supervised 3D action representation learning with cross-modal mutual distillation. In ECCV.","DOI":"10.1007\/978-3-031-20062-5_42"},{"key":"2644_CR61","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.neucom.2023.03.070","volume":"537","author":"Q Men","year":"2023","unstructured":"Men, Q., Ho, E. S. L., Shum, H. P. H., & Leung, H. (2023). Focalized contrastive view-invariant learning for self-supervised skeleton-based action recognition. Neurocomputing, 537, 198\u2013209.","journal-title":"Neurocomputing"},{"key":"2644_CR62","doi-asserted-by":"crossref","unstructured":"Nie, Q., Liu, Z., & Liu, Y. (2020). Unsupervised 3D human pose representation with viewpoint and pose disentanglement. In ECCV.","DOI":"10.1007\/978-3-030-58529-7_7"},{"key":"2644_CR63","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., & El-Nouby, A., et\u00a0al. (2023). Dinov2: Learning robust visual features without supervision. arXiv:2304.07193."},{"key":"2644_CR64","unstructured":"Paoletti, G., Cavazza, J., Beyan, C., & Del\u00a0Bue, A. Unsupervised human action recognition with skeletal graph laplacian and self-supervised viewpoints invariance. arXiv:2204.10312."},{"key":"2644_CR65","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., & Varol, G. (2023). Tmr: Text-to-motion retrieval using contrastive 3d human motion synthesis. In ICCV, pages 9488\u20139497.","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"2644_CR66","unstructured":"Qi, Z., Dong, R., Fan, G., Ge, Z., Zhang, X., Ma, K., & Yi, L. (2023). Contrast with reconstruct: Contrastive 3D representation learning guided by generative pretraining. arXiv:2302.02318, 2023."},{"issue":"1","key":"2644_CR67","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1007\/s11263-023-01864-0","volume":"132","author":"H Rao","year":"2024","unstructured":"Rao, H., Leung, C., & Miao, C. (2024). Hierarchical skeleton meta-prototype contrastive learning with hard skeleton mining for unsupervised person re-identification. IJCV, 132(1), 238\u2013260.","journal-title":"IJCV"},{"key":"2644_CR68","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., Shihao, X., Xiping, H., Cheng, J., & Bin, H. (2021). Augmented skeleton based contrastive action learning with momentum lstm for unsupervised action recognition. Information Sciences, 569, 90\u2013109.","journal-title":"Information Sciences"},{"key":"2644_CR69","unstructured":"Robinson, J., Chuang, C.-Y., Sra, S., & Jegelka, S. (2020). Contrastive learning with hard negative samples. arXiv:2010.04592"},{"key":"2644_CR70","doi-asserted-by":"crossref","unstructured":"Shah, A., Roy, A., Shah, K., Mishra, S.K., Jacobs, D., Cherian, A., & Chellappa, R. (2023). Halp: Hallucinating latent positives for skeleton-based self-supervised learning of actions. arXiv:2304.00387","DOI":"10.1109\/CVPR52729.2023.01807"},{"key":"2644_CR71","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.-T., & Wang, G. (2016). NTU RGB-D: A large scale dataset for 3D human activity analysis. In IEEE CVPR.","DOI":"10.1109\/CVPR.2016.115"},{"key":"2644_CR72","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., & Lu, H. (2019). Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In IEEE CVPR.","DOI":"10.1109\/CVPR.2019.01230"},{"key":"2644_CR73","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., & Lu, H. (2020). Decoupled spatial-temporal attention network for skeleton-based action recognition.","DOI":"10.1007\/978-3-030-69541-5_3"},{"key":"2644_CR74","doi-asserted-by":"crossref","unstructured":"Shu, X., Xu, B., Zhang, L., & Tang, J. (2022). Multi-granularity anchor-contrastive representation learning for semi-supervised skeleton-based action recognition. IEEE TPAMI.","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"2644_CR75","doi-asserted-by":"crossref","unstructured":"Shurrab, S., & Duwairi, R. (2022). Self-supervised learning methods and applications in medical imaging analysis: A survey. PeerJ Computer Science, 8, Article e1045.","DOI":"10.7717\/peerj-cs.1045"},{"key":"2644_CR76","doi-asserted-by":"crossref","unstructured":"Song, Y.-F., Zhang, Z., & Wang, L. (2019). Richly activated graph convolutional network for action recognition with incomplete skeletons. In IEEE ICIP.","DOI":"10.1109\/ICIP.2019.8802917"},{"key":"2644_CR77","doi-asserted-by":"crossref","unstructured":"Su, K., Liu, X., & Shlizerman, E. (2020) Predict & cluster: Unsupervised skeleton based action recognition. In IEEE CVPR.","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"2644_CR78","doi-asserted-by":"crossref","unstructured":"Su, Y., Lin, G., & Wu, Q. (2021). Self-supervised 3D skeleton action representation learning with motion consistency and continuity. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01308"},{"key":"2644_CR79","doi-asserted-by":"crossref","unstructured":"Sun, S., Liu, D., Dong, J., Qu, X., Gao, J., Yang, X., Wang, X., & Wang, M. (2023). Unified multi-modal unsupervised representation learning for skeleton-based action understanding. In ACM MM.","DOI":"10.1145\/3581783.3612449"},{"key":"2644_CR80","doi-asserted-by":"crossref","unstructured":"Tanfous, A.B., Zerroug, A., Linsley, D., & Serre, T. (2022). How and what to learn: Taxonomizing self-supervised learning for 3D action recognition. In IEEE WACV.","DOI":"10.1109\/WACV51458.2022.00294"},{"key":"2644_CR81","doi-asserted-by":"crossref","unstructured":"Thoker, F.M., Doughty, H., & Snoek, C.G.M. (2021). Skeleton-contrastive 3d action representation learning. In ACM MM.","DOI":"10.1145\/3474085.3475307"},{"key":"2644_CR82","first-page":"6827","volume":"33","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmid, C., & Isola, P. (2020). What makes for good views for contrastive learning? NeurIPS, 33, 6827\u20136839.","journal-title":"NeurIPS"},{"key":"2644_CR83","unstructured":"Tong, Z., Song, Y., & Wang, J. (2022). and Limin Wang. VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training. NeurIPS."},{"key":"2644_CR84","doi-asserted-by":"crossref","unstructured":"Von\u00a0Marcard, T., Henschel, R., Black, M.J., Rosenhahn, B., & Pons-Moll, G. (2018). Recovering accurate 3D human pose in the wild using imus and a moving camera. In ECCV.","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"2644_CR85","doi-asserted-by":"crossref","unstructured":"Wang, M., Li, X., Chen, S., Zhang, X., Ma, L., & Zhang, Y. (2023). Learning representations by contrastive spatio-temporal clustering for skeleton-based action recognition. IEEE TMM.","DOI":"10.1109\/TMM.2023.3307933"},{"key":"2644_CR86","first-page":"6224","volume":"31","author":"P Wang","year":"2022","unstructured":"Wang, P., Wen, J., Si, C., Qian, Y., & Wang, L. (2022). Contrast-reconstruction representation learning for self-supervised skeleton-based action recognition. IEEE TIP, 31, 6224\u20136238.","journal-title":"IEEE TIP"},{"issue":"5","key":"2644_CR87","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S. E., Bronstein, M. M., & Solomon, J. M. (2019). Dynamic graph cnn for learning on point clouds. IEEE TOG, 38(5), 1\u201312.","journal-title":"IEEE TOG"},{"key":"2644_CR88","doi-asserted-by":"crossref","unstructured":"Weng, W., Wang, H., Wang, J., & He, L. (2025). and Guosen Xie. Usdrl: Unified skeleton-based dense representation learning with multi-grained feature decorrelation. In AAAI.","DOI":"10.1609\/aaai.v39i8.32899"},{"key":"2644_CR89","doi-asserted-by":"crossref","unstructured":"Wu, L., Lin, L., Zhang, J., Ma, Y., & Liu, J. (2024). Macdiff: Unified skeleton modeling with masked conditional diffusion. In ECCV, pages 110\u2013128.","DOI":"10.1007\/978-3-031-73347-5_7"},{"key":"2644_CR90","doi-asserted-by":"crossref","unstructured":"Wu, W., Hua, Y., Wu, S., Chen, C., & Lu, A., et\u00a0al. (2022). Skeletonmae: Spatial-temporal masked autoencoders for self-supervised skeleton action recognition. arXiv:2209.02399","DOI":"10.1109\/ICMEW59549.2023.00045"},{"key":"2644_CR91","unstructured":"Xie, J., Li, W., Zhan, X., Liu, Z., Ong, Y.S., & Loy, C.C. (2022). Masked frequency modeling for self-supervised visual pre-training. arXiv:2206.07706"},{"issue":"12","key":"2644_CR92","doi-asserted-by":"publisher","first-page":"2994","DOI":"10.1007\/s11263-022-01681-x","volume":"130","author":"J Xie","year":"2022","unstructured":"Xie, J., Zhan, X., Liu, Z., Ong, Y.-S., & Loy, C. C. (2022). Delving into inter-image invariance for unsupervised visual representations. IJCV, 130(12), 2994\u20133013.","journal-title":"IJCV"},{"key":"2644_CR93","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., Cao, Y., Lin, Y., Bao, J., Yao, Z., & Dai, Q. (2022b). and Han Hu. Simmim: A simple framework for masked image modeling. In IEEE CVPR.","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"2644_CR94","first-page":"3852","volume":"31","author":"B Xu","year":"2022","unstructured":"Xu, B., Shu, X., & Song, Y. (2022). X-invariant contrastive augmentation and representation learning for semi-supervised skeleton-based action recognition. IEEE TIP, 31, 3852\u20133867.","journal-title":"IEEE TIP"},{"key":"2644_CR95","doi-asserted-by":"crossref","unstructured":"Xu, D., Xiao, J., Zhao, Z., Shao, J., Xie, D., Zhuang, Y. (2019). Self-supervised spatiotemporal learning via video clip order prediction. In IEEE CVPR.","DOI":"10.1109\/CVPR.2019.01058"},{"key":"2644_CR96","unstructured":"Xu, S., Rao, H., Hu, X., Cheng, J., & Hu, B. (2021a). and Bin Hu. Prototypical contrast and reverse prediction: Unsupervised skeleton based action recognition. IEEE TMM."},{"key":"2644_CR97","unstructured":"Xu, Z., Shen, X., Wong, Y., & Kankanhalli, M.S. (2021b). Unsupervised motion representation learning with capsule autoencoders. NeurIPS."},{"key":"2644_CR98","doi-asserted-by":"crossref","unstructured":"Yan, H., Liu, Y., Wei, Y., Li, Z., Li, G., & Lin, L. (2023). SkeletonMAE: graph-based masked autoencoder for skeleton sequence pre-training. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00516"},{"key":"2644_CR99","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., & Lin, D. (2018). Spatial temporal graph convolutional networks for skeleton-based action recognition. In AAAI, pages 7444\u20137452, 2018.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"2644_CR100","doi-asserted-by":"crossref","unstructured":"Yang, D., Wang, Y., Dantcheva, A., Garattoni, L., Francesca, G., & Br\u00e9mond, F. (2024). View-invariant skeleton action representation learning via motion retargeting. IJCV, pages 1\u201316.","DOI":"10.1007\/s11263-023-01967-8"},{"key":"2644_CR101","doi-asserted-by":"crossref","unstructured":"Yang, S., Liu, J., Lu, S., Er, M.H., & Kot, A.C. (2021). Skeleton cloud colorization for unsupervised 3D action representation learning. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01317"},{"key":"2644_CR102","unstructured":"Yang, S., Liu, J., Lu, S., Hwa, E.M., Hu, Y., & Kot, A.C. (20223) Self-supervised 3d action representation learning with skeleton cloud colorization. arXiv:2304.08799"},{"issue":"12","key":"2644_CR103","first-page":"8623","volume":"32","author":"Y Yang","year":"2022","unstructured":"Yang, Y., Liu, G., & Gao, X. (2022). Motion guided attention learning for self-supervised 3D human action recognition. IEEE TCSVT, 32(12), 8623\u20138634.","journal-title":"IEEE TCSVT"},{"key":"2644_CR104","doi-asserted-by":"crossref","unstructured":"Yu, Q., Tanaka, M., & Fujiwara, K. (2024). Exploring vision transformers for 3d human motion-language models with motion patches. In IEEE CVPR, pages 937\u2013946.","DOI":"10.1109\/CVPR52733.2024.00095"},{"key":"2644_CR105","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., & Deny, S. (2021). Barlow twins: Self-supervised learning via redundancy reduction. In International Conference on Machine Learning, pages 12310\u201312320. PMLR."},{"key":"2644_CR106","first-page":"03065","volume":"2207","author":"C Zhan","year":"2022","unstructured":"Zhan, C., Hong, L., Tianyu, G., Zhengyan, C., Pinhao, S., & Hao, T. (2022). Contrastive learning from spatio-temporal mixed skeleton sequences for self-supervised skeleton-based action recognition. In arXiv, 2207, 03065.","journal-title":"In arXiv"},{"key":"2644_CR107","doi-asserted-by":"crossref","unstructured":"Zhan, X., Xie, J., Liu, Z., Ong, Y.-S., & Loy, C.C. (2020). Online deep clustering for unsupervised representation learning. In IEEE CVPR, pages 6688\u20136697.","DOI":"10.1109\/CVPR42600.2020.00672"},{"key":"2644_CR108","doi-asserted-by":"crossref","unstructured":"Zhang, H., & Hou, Y. (2022). and Wenjing Zhang. Skeletal twins: Unsupervised skeleton-based action representation learning.","DOI":"10.1109\/ICME52920.2022.9859595"},{"key":"2644_CR109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_3","volume-title":"Contrastive positive mining for unsupervised 3D action representation learning","author":"H Zhang","year":"2022","unstructured":"Zhang, H., Hou, Y., Zhang, W., & Li, W. (2022). Contrastive positive mining for unsupervised 3D action representation learning. In ECCV: Springer."},{"key":"2644_CR110","first-page":"2023","volume":"I","author":"J Zhang","year":"2023","unstructured":"Zhang, J., Lin, L., & Liu, J. (2023). Hierarchical consistent contrastive learning for skeleton-based action recognition with growing augmentations. In AAA, I, 2023.","journal-title":"In AAA"},{"key":"2644_CR111","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lin, L., & Liu, J. (2023). Prompted contrast with masked motion modeling: Towards versatile 3d action representation learning. In ACM MM.","DOI":"10.1145\/3581783.3611774"},{"key":"2644_CR112","unstructured":"Zhang, Q., & Wang, Y. (2022). and Yisen Wang. How mask matters: Towards theoretical understandings of masked autoencoders. NeurIPS."},{"key":"2644_CR113","doi-asserted-by":"crossref","unstructured":"Zheng, N., Wen, J., Liu, R., Long, L., Dai, J., & Gong, Z. (2018). Unsupervised representation learning with long-term dynamics for skeleton based action recognition. In AAAI.","DOI":"10.1609\/aaai.v32i1.11853"},{"key":"2644_CR114","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Q., & Wang, Y. (2023a). Learning discriminative representations for skeleton based action recognition. In IEEE CVPR.","DOI":"10.1109\/CVPR52729.2023.01022"},{"key":"2644_CR115","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Duan, H., Rao, A., Su, B., & Wang, J. (2023b). Self-supervised action representation learning from partial spatio-temporal skeleton sequences. arXiv:2302.09018.","DOI":"10.1609\/aaai.v37i3.25495"},{"key":"2644_CR116","doi-asserted-by":"crossref","unstructured":"Zhu, W., Ma, X., Liu, Z., Liu, L., & Wayne, W. (2023). and Yizhou Wang. Motionbert: A unified perspective on learning human motion representations. In ICCV.","DOI":"10.1109\/ICCV51070.2023.01385"},{"key":"2644_CR117","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Han, H., Yu, Z., & Liu, G. (2023). Modeling the relative visual tempo for self-supervised skeleton-based action recognition. In ICCV.","DOI":"10.1109\/ICCV51070.2023.01279"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02644-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02644-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02644-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T15:43:55Z","timestamp":1771602235000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02644-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":117,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["2644"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02644-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"3 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This work was supported in part by the Beijing Major Science and Technology Project under Contract No. Z251100008425023, in part by the National Natural Science Foundation of China under Grant 62471009, and in part by the Key Laboratory of Science, Technology and Standard in Press Industry (Key Laboratory of Intelligent Press Media Technology).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"38"}}