{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T03:10:39Z","timestamp":1790910639325,"version":"4.1.0"},"publisher-location":"Cham","reference-count":69,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733468","type":"print"},{"value":"9783031733475","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73347-5_5","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T05:15:43Z","timestamp":1730092543000},"page":"75-92","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Idempotent Unsupervised Representation Learning for\u00a0Skeleton-Based Action Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3229-4096","authenticated-orcid":false,"given":"Lilang","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1155-5577","authenticated-orcid":false,"given":"Lehong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5039-8916","authenticated-orcid":false,"given":"Jiahang","family":"Zhang","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":[[2024,10,29]]},"reference":[{"key":"5_CR1","unstructured":"Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. In: Proceedings of the Advances in Neural Information Processing Systems (2019)"},{"key":"5_CR2","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Proceedings of the International Conference for Machine Learning (2020)"},{"key":"5_CR3","doi-asserted-by":"publisher","unstructured":"Chen, Y., et al.: Hierarchically self-supervised transformer for\u00a0human Skeleton representation learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part XXVI, pp. 185\u2013202. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_11","DOI":"10.1007\/978-3-031-19809-0_11"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., Hu, W.: Channel-wise topology refinement graph convolution for skeleton-based action recognition. In: Proceedings of the International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"5_CR5","unstructured":"Chen, Z., Liu, H., Guo, T., Chen, Z., Song, P., Tang, H.: Contrastive learning from spatio-temporal mixed skeleton sequences for self-supervised skeleton-based action recognition. arXiv preprint arXiv:2207.03065 (2022)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, K., Zhang, Y., He, X., Chen, W., Cheng, J., Lu, H.: Skeleton-based action recognition with shift graph convolutional network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 183\u2013192 (2020)","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"5_CR7","unstructured":"Du, T., Wang, Y., Wang, Y.: On the role of discrete tokenization in visual representation learning. In: Proceedings of the International Conference on Learning Representations (2023)"},{"key":"5_CR8","unstructured":"Erhan, D., Bengio, Y., Courville, A., Manzagol, P.A., Vincent, P., Bengio, S.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11, 625\u2013660 (2010)"},{"key":"5_CR9","unstructured":"Feichtenhofer, C., Li, Y., He, K., et\u00a0al.: Masked autoencoders as spatiotemporal learners. Adv. Neural Inf. Process. Syst. 35, 35946\u201335958 (2022)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Goutsu, Y., Takano, W., Nakamura, Y.: Motion recognition employing multiple kernel learning of fisher vectors using local skeleton features. In: Proceedings of the International Conference for Machine Learning Workshops (2015)","DOI":"10.1109\/ICCVW.2015.50"},{"key":"5_CR11","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. Proc. AAAI Conf. Artif. Intell. 36(1), 762\u2013770 (2022)","DOI":"10.1609\/aaai.v36i1.19957"},{"key":"5_CR12","unstructured":"Guo, X., Wang, Y., Du, T., Wang, Y.: Contranorm: a contrastive learning perspective on oversmoothing and beyond. arXiv preprint arXiv:2303.06562 (2023)"},{"key":"5_CR13","unstructured":"HaoChen, J., Wei, C., Gaidon, A., Ma, T.: Provable guarantees for self-supervised deep learning with spectral contrastive loss. arXiv preprint arXiv:2106.04156 (2021)"},{"key":"5_CR14","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\u00a0IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"5_CR15","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Proc. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)"},{"key":"5_CR16","unstructured":"Isola, P., Zoran, D., Krishnan, D., Adelson, E.H.: Learning visual groups from co-occurrences in space and time. arXiv:1511.06811 (2015)"},{"key":"5_CR17","unstructured":"Jang, E., Devin, C., Vanhoucke, V., Levine, S.: Grasp2Vec: learning object representations from self-supervised grasping. arXiv preprint arXiv:1811.06964 (2018)"},{"key":"5_CR18","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. Proceedings of the European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19772-7_13"},{"key":"5_CR19","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 Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"5_CR20","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 ACM International Conference on Multimedia (2020)","DOI":"10.1145\/3394171.3413548"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Lin, L., Zhang, J., Liu, J.: Actionlet-dependent contrastive learning for unsupervised skeleton-based action recognition. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00234"},{"key":"5_CR22","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. Multim. Comput. Commun. Appl. (2020)","DOI":"10.1145\/3365212"},{"key":"5_CR23","doi-asserted-by":"crossref","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. (2019)","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"5_CR24","unstructured":"Liu, X., Wang, Z., Li, Y.L., Wang, S.: Self-supervised learning via maximum entropy coding. Adv. Neural Inf. Process. Syst. 35, 34091\u201334105 (2022)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, H., Chen, Z., Wang, Z., Ouyang, W.: Disentangling and unifying graph convolutions for skeleton-based action recognition. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Lorre, G., Rabarisoa, J., Orcesi, A., Ainouz, S., Canu, S.: Temporal contrastive pretraining for video action recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 662\u2013670 (2020)","DOI":"10.1109\/WACV45572.2020.9093278"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Lv, F., Nevatia, R.: Recognition and segmentation of 3-d human action using HMM and multi-class adaboost. In: Proceedings of the European Conference on Computer Vision (2006)","DOI":"10.1007\/11744085_28"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Mao, Y., Deng, J., Zhou, W., Fang, Y., Ouyang, W., Li, H.: Masked motion predictors are strong 3d action representation learners. In: Proceedings of the International Conference on Computer Vision, pp. 10181\u201310191 (2023)","DOI":"10.1109\/ICCV51070.2023.00934"},{"key":"5_CR29","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: Proceedings of the European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-20062-5_42"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Newey, W.K.: Adaptive estimation of regression models via moment restrictions. J. Economet. (1988)","DOI":"10.1016\/0304-4076(88)90048-6"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: Proceedings of the European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"5_CR32","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 (2020)","DOI":"10.1609\/aaai.v34i03.5652"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Rai, N., Adeli, E., Lee, K.H., Gaidon, A., Niebles, J.C.: Cocon: cooperative-contrastive learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3384\u20133393 (2021)","DOI":"10.1109\/CVPRW53098.2021.00377"},{"key":"5_CR34","doi-asserted-by":"crossref","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. (2021)","DOI":"10.1016\/j.ins.2021.04.023"},{"key":"5_CR35","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 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Skeleton-based action recognition with directed graph neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7912\u20137921 (2019)","DOI":"10.1109\/CVPR.2019.00810"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Shotton, J., et al.: Real-time human pose recognition in parts from single depth images. Commun. ACM (2013)","DOI":"10.1007\/978-3-642-28661-2_5"},{"key":"5_CR39","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 (2019)","DOI":"10.1109\/CVPR.2019.00132"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Si, C., Jing, Y., Wang, W., Wang, L., Tan, T.: Skeleton-based action recognition with spatial reasoning and temporal stack learning. In: Proceedings of the European Conference on Computer Vision, pp. 103\u2013118 (2018)","DOI":"10.1007\/978-3-030-01246-5_7"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Song, Y.F., Zhang, Z., Shan, C., Wang, L.: Constructing stronger and faster baselines for skeleton-based action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 1474\u20131488 (2022)","DOI":"10.1109\/TPAMI.2022.3157033"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Song, Y., Zhang, Z., Shan, C., Wang, L.: Stronger, faster and more explainable: a graph convolutional baseline for skeleton-based action recognition. In: Proceedings of the ACM International Conference on Multimedia (2020)","DOI":"10.1145\/3394171.3413802"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Su, K., Liu, X., Shlizerman, E.: Predict and cluster: unsupervised skeleton based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Tao, L., Vidal, R.: Moving poselets: a discriminative and interpretable skeletal motion representation for action recognition. In: Proceedings of the International Conference for Machine Learning Workshops (2015)","DOI":"10.1109\/ICCVW.2015.48"},{"key":"5_CR45","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model. arXiv preprint arXiv:2209.14916 (2022)"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Thoker, F.M., Doughty, H., Snoek, C.G.: Skeleton-contrastive 3D action representation learning. In: Proceedings of the ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475307"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. arXiv preprint arXiv:1906.05849 (2019)","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"5_CR48","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":"5_CR49","doi-asserted-by":"crossref","unstructured":"Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3d skeletons as points in a lie group. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.82"},{"key":"5_CR50","doi-asserted-by":"crossref","unstructured":"Vemulapalli, R., Chellapa, R.: Rolling rotations for recognizing human actions from 3d skeletal data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.484"},{"key":"5_CR51","unstructured":"Wang, J., Liu, Z., Wu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2012)"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Wang, P., Yuan, C., Hu, W., Li, B., Zhang, Y.: Graph based skeleton motion representation and similarity measurement for action recognition. In: Proceedings of the European Conference on Computer Vision, pp. 370\u2013385 (2016)","DOI":"10.1007\/978-3-319-46478-7_23"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Wang, P., Wen, J., Si, C., Qian, Y., Wang, L.: Contrast-reconstruction representation learning for self-supervised skeleton-based action recognition. IEEE Trans. Image Process. 31, 6224\u20136238 (2022)","DOI":"10.1109\/TIP.2022.3207577"},{"key":"5_CR54","unstructured":"Wang, Y., Zhang, Q., Du, T., Yang, J., Lin, Z., Wang, Y.: A message passing perspective on learning dynamics of contrastive learning. arXiv preprint arXiv:2303.04435 (2023)"},{"key":"5_CR55","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C.Y., Yuille, A., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 14668\u201314678 (2022)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"5_CR56","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 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"5_CR57","unstructured":"Xu, T., et\u00a0al.: Idempotence and perceptual image compression. arXiv preprint arXiv:2401.08920 (2024)"},{"key":"5_CR58","doi-asserted-by":"crossref","unstructured":"Yan, H., Liu, Y., Wei, Y., Li, Z., Li, G., Lin, L.: Skeletonmae: graph-based masked autoencoder for skeleton sequence pre-training. In: Proceedings of the International Conference on Computer Vision, pp. 5606\u20135618 (2023)","DOI":"10.1109\/ICCV51070.2023.00516"},{"key":"5_CR59","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"5_CR60","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 International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01317"},{"key":"5_CR61","doi-asserted-by":"crossref","unstructured":"Yang, S., Liu, J., Lu, S., Hwa, E.M., Hu, Y., Kot, A.C.: Self-supervised 3d action representation learning with skeleton cloud colorization. IEEE Transaction on Pattern Analysis and Machine Intelligence (2023)","DOI":"10.1109\/TPAMI.2023.3325463"},{"key":"5_CR62","doi-asserted-by":"crossref","unstructured":"Ye, M., Zhang, X., Yuen, P.C., Chang, S.F.: Unsupervised embedding learning via invariant and spreading instance feature. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00637"},{"key":"5_CR63","unstructured":"Yu, Y., Chan, K.H.R., You, C., Song, C., Ma, Y.: Learning diverse and discriminative representations via the principle of maximal coding rate reduction. Proc. Adv. Neural Inf. Process. Syst. 33, 9422\u20139434 (2020)"},{"key":"5_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hou, Y., Zhang, W., Li, W.: Contrastive positive mining for unsupervised 3d action representation learning. In: Proceedings of the European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19772-7_3"},{"key":"5_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lin, L., Liu, J.: Prompted contrast with masked motion modeling: towards versatile 3d action representation learning. In: Proceedings of the ACM International Conference on Multimedia, pp. 7175\u20137183 (2023)","DOI":"10.1145\/3581783.3611774"},{"key":"5_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, P., Lan, C., Zeng, W., Xing, J., Xue, J., Zheng, N.: Semantics-guided neural networks for efficient skeleton-based human action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00119"},{"key":"5_CR67","unstructured":"Zhang, Q., Wang, Y., Wang, Y.: How mask matters: towards theoretical understandings of masked autoencoders. Proc. Adv. Neural Inf. Process. Syst. 35, 27127\u201327139 (2022)"},{"key":"5_CR68","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 Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01434"},{"key":"5_CR69","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 (2018)","DOI":"10.1609\/aaai.v32i1.11853"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73347-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T05:40:28Z","timestamp":1730094028000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73347-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031733468","9783031733475"],"references-count":69,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73347-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}