{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T22:23:09Z","timestamp":1776982989356,"version":"3.51.4"},"publisher-location":"Cham","reference-count":77,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729393","type":"print"},{"value":"9783031729409","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T00:00:00Z","timestamp":1731801600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T00:00:00Z","timestamp":1731801600000},"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\/978-3-031-72940-9_23","type":"book-chapter","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T20:41:09Z","timestamp":1731789669000},"page":"401-420","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":53,"title":["SkateFormer: Skeletal-Temporal Transformer for\u00a0Human Action Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0030-0129","authenticated-orcid":false,"given":"Jeonghyeok","family":"Do","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0146-5419","authenticated-orcid":false,"given":"Munchurl","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,17]]},"reference":[{"key":"23_CR1","unstructured":"Cai, D., Kang, Y., Yao, A., Chen, Y.: Ske2Grid: skeleton-to-grid representation learning for action recognition. In: International Conference on Machine Learning (2023)"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"23_CR3","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 IEEE\/CVF International Conference on Computer Vision, pp. 13359\u201313368 (2021)","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, S., Yang, B., Li, Q., Liu, H.: Multi-scale spatial temporal graph convolutional network for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1113\u20131122 (2021)","DOI":"10.1609\/aaai.v35i2.16197"},{"key":"23_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/978-3-030-58586-0_32","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Cheng","year":"2020","unstructured":"Cheng, K., Zhang, Y., Cao, C., Shi, L., Cheng, J., Lu, H.: Decoupling GCN with DropGraph module for skeleton-based action recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 536\u2013553. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_32"},{"key":"23_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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 183\u2013192 (2020)","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Chi, H.G., Ha, M.H., Chi, S., Lee, S.W., Huang, Q., Ramani, K.: InfoGCN: representation learning for human skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20186\u201320196 (2022)","DOI":"10.1109\/CVPR52688.2022.01955"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Ding, Z., Wang, P., Ogunbona, P.O., Li, W.: Investigation of different skeleton features for CNN-based 3D action recognition. In: 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pp. 617\u2013622. IEEE (2017)","DOI":"10.1109\/ICMEW.2017.8026286"},{"key":"23_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Duan, H., Wang, J., Chen, K., Lin, D.: PYSKL: towards good practices for skeleton action recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 7351\u20137354 (2022)","DOI":"10.1145\/3503161.3548546"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Duan, H., et al.: SkeleTR: towards skeleton-based action recognition in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13634\u201313644 (2023)","DOI":"10.1109\/ICCV51070.2023.01254"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., Lin, D., Dai, B.: Revisiting skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2969\u20132978 (2022)","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"23_CR13","unstructured":"Gao, Z., et al.: Focal and global spatial-temporal transformer for skeleton-based action recognition. In: Proceedings of the Asian Conference on Computer Vision, pp. 382\u2013398 (2022)"},{"key":"23_CR14","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.\u00a036, pp. 762\u2013770 (2022)","DOI":"10.1609\/aaai.v36i1.19957"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2462\u20132470 (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"23_CR16","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"issue":"6","key":"23_CR17","doi-asserted-by":"publisher","first-page":"2842","DOI":"10.1109\/TIP.2018.2812099","volume":"27","author":"Q Ke","year":"2018","unstructured":"Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: Learning clip representations for skeleton-based 3D action recognition. IEEE Trans. Image Process. 27(6), 2842\u20132855 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR18","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"23_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1007\/978-3-030-58565-5_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Korban","year":"2020","unstructured":"Korban, M., Li, X.: DDGCN: a dynamic directed graph convolutional network for action recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 761\u2013776. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_45"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Kwon, T., Tekin, B., St\u00fchmer, J., Bogo, F., Pollefeys, M.: H2O: two hands manipulating objects for first person interaction recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10138\u201310148 (2021)","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Lee, J., Lee, M., Cho, S., Woo, S., Jang, S., Lee, S.: Leveraging spatio-temporal dependency for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10255\u201310264 (2023)","DOI":"10.1109\/ICCV51070.2023.00941"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Lee, J., Lee, M., Lee, D., Lee, S.: Hierarchically decomposed graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10444\u201310453 (2023)","DOI":"10.1109\/ICCV51070.2023.00958"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Li, B., Dai, Y., Cheng, X., Chen, H., Lin, Y., He, M.: Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN. In: 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pp. 601\u2013604. IEEE (2017)","DOI":"10.1109\/ICMEW.2017.8026282"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, S., Chen, X., Zhang, Y., Wang, Y., Tian, Q.: Actional-structural graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3595\u20133603 (2019)","DOI":"10.1109\/CVPR.2019.00371"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Li, S., Li, W., Cook, C., Zhu, C., Gao, Y.: Independently recurrent neural network (IndRNN): Building a longer and deeper RNN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5457\u20135466 (2018)","DOI":"10.1109\/CVPR.2018.00572"},{"key":"23_CR26","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"},{"issue":"10","key":"23_CR27","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."},{"key":"23_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1007\/978-3-319-46487-9_50","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Liu","year":"2016","unstructured":"Liu, J., Shahroudy, A., Xu, D., Wang, G.: Spatio-temporal LSTM with trust gates for 3D human action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 816\u2013833. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_50"},{"issue":"4","key":"23_CR29","doi-asserted-by":"publisher","first-page":"1586","DOI":"10.1109\/TIP.2017.2785279","volume":"27","author":"J Liu","year":"2017","unstructured":"Liu, J., Wang, G., Duan, L.Y., Abdiyeva, K., Kot, A.C.: Skeleton-based human action recognition with global context-aware attention LSTM networks. IEEE Trans. Image Process. 27(4), 1586\u20131599 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"23_CR31","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"23_CR32","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"23_CR33","unstructured":"M\u00fcller, R., Kornblith, S., Hinton, G.E.: When does label smoothing help? In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"23_CR34","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/978-3-031-19806-9_35","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXV","author":"Y Pang","year":"2022","unstructured":"Pang, Y., Ke, Q., Rahmani, H., Bailey, J., Liu, J.: IGFormer: interaction graph transformer for\u00a0skeleton-based human interaction recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXV, pp. 605\u2013622. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19806-9_35"},{"key":"23_CR35","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch (2017)"},{"key":"23_CR36","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.\u00a034, pp. 2669\u20132676 (2020)","DOI":"10.1609\/aaai.v34i03.5652"},{"key":"23_CR37","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1109\/TMM.2021.3050642","volume":"24","author":"M Perez","year":"2021","unstructured":"Perez, M., Liu, J., Kot, A.C.: Interaction relational network for mutual action recognition. IEEE Trans. Multimedia 24, 366\u2013376 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"23_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103219","volume":"208","author":"C Plizzari","year":"2021","unstructured":"Plizzari, C., Cannici, M., Matteucci, M.: Skeleton-based action recognition via spatial and temporal transformer networks. Comput. Vis. Image Underst. 208, 103219 (2021)","journal-title":"Comput. Vis. Image Underst."},{"key":"23_CR39","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.patcog.2015.11.019","volume":"53","author":"LL Presti","year":"2016","unstructured":"Presti, L.L., La Cascia, M.: 3D skeleton-based human action classification: a survey. Pattern Recogn. 53, 130\u2013147 (2016)","journal-title":"Pattern Recogn."},{"key":"23_CR40","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.neucom.2022.10.084","volume":"518","author":"H Qiu","year":"2023","unstructured":"Qiu, H., Hou, B., Ren, B., Zhang, X.: Spatio-temporal segments attention for skeleton-based action recognition. Neurocomputing 518, 30\u201338 (2023)","journal-title":"Neurocomputing"},{"key":"23_CR41","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":"23_CR42","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7912\u20137921 (2019)","DOI":"10.1109\/CVPR.2019.00810"},{"key":"23_CR43","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12026\u201312035 (2019)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Decoupled spatial-temporal attention network for skeleton-based action-gesture recognition. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69541-5_3"},{"key":"23_CR45","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1227\u20131236 (2019)","DOI":"10.1109\/CVPR.2019.00132"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Song, Y.F., Zhang, Z., Shan, C., Wang, L.: Stronger, faster and more explainable: a graph convolutional baseline for skeleton-based action recognition. In: proceedings of the 28th ACM International Conference on Multimedia, pp. 1625\u20131633 (2020)","DOI":"10.1145\/3394171.3413802"},{"issue":"2","key":"23_CR47","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.1109\/TPAMI.2022.3157033","volume":"45","author":"YF Song","year":"2022","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)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR48","unstructured":"Sovrasov, V.: ptflops: a flops counting tool for neural networks in PyTorch framework (2018\u20132023). https:\/\/github.com\/sovrasov\/flops-counter.pytorch"},{"key":"23_CR49","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-NET: CNNs for optical flow using pyramid, warping, and cost volume. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8934\u20138943 (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"23_CR50","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"23_CR51","doi-asserted-by":"crossref","unstructured":"Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., Liu, J.: Human action recognition from various data modalities: a review. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"23_CR52","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"23_CR53","doi-asserted-by":"crossref","unstructured":"Tu, Z., Talebi, H., Zhang, H., Yang, F., Milanfar, P., Bovik, A., Li, Y.: MAXIM: multi-axis MLP for image processing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5769\u20135780 (2022)","DOI":"10.1109\/CVPR52688.2022.00568"},{"key":"23_CR54","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/978-3-031-20053-3_27","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXIV","author":"Z Tu","year":"2022","unstructured":"Tu, Z., et al.: MaxViT: multi-axis vision transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXIV, pp. 459\u2013479. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_27"},{"key":"23_CR55","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"23_CR56","doi-asserted-by":"crossref","unstructured":"Wang, J., Nie, X., Xia, Y., Wu, Y., Zhu, S.C.: Cross-view action modeling, learning and recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2649\u20132656 (2014)","DOI":"10.1109\/CVPR.2014.339"},{"key":"23_CR57","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/TIP.2019.2925285","volume":"29","author":"L Wang","year":"2019","unstructured":"Wang, L., Huynh, D.Q., Koniusz, P.: A comparative review of recent kinect-based action recognition algorithms. IEEE Trans. Image Process. 29, 15\u201328 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR58","doi-asserted-by":"crossref","unstructured":"Wang, L., Koniusz, P.: 3Mformer: multi-order multi-mode transformer for skeletal action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5620\u20135631 (2023)","DOI":"10.1109\/CVPR52729.2023.00544"},{"key":"23_CR59","doi-asserted-by":"crossref","unstructured":"Wang, P., Li, Z., Hou, Y., Li, W.: Action recognition based on joint trajectory maps using convolutional neural networks. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 102\u2013106 (2016)","DOI":"10.1145\/2964284.2967191"},{"key":"23_CR60","doi-asserted-by":"crossref","unstructured":"Wang, Q., Shi, S., He, J., Peng, J., Liu, T., Weng, R.: IIP-transformer: intra-inter-part transformer for skeleton-based action recognition. In: 2023 IEEE International Conference on Big Data (BigData), pp. 936\u2013945. IEEE (2023)","DOI":"10.1109\/BigData59044.2023.10386970"},{"key":"23_CR61","doi-asserted-by":"crossref","unstructured":"Wang, X., Xu, X., Mu, Y.: Neural koopman pooling: control-inspired temporal dynamics encoding for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10597\u201310607 (2023)","DOI":"10.1109\/CVPR52729.2023.01021"},{"key":"23_CR62","doi-asserted-by":"crossref","unstructured":"Wen, Y., Tang, Z., Pang, Y., Ding, B., Liu, M.: Interactive spatiotemporal token attention network for skeleton-based general interactive action recognition. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7886\u20137892. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10342472"},{"key":"23_CR63","doi-asserted-by":"crossref","unstructured":"Xiang, W., Li, C., Zhou, Y., Wang, B., Zhang, L.: Generative action description prompts for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10276\u201310285 (2023)","DOI":"10.1109\/ICCV51070.2023.00943"},{"key":"23_CR64","doi-asserted-by":"crossref","unstructured":"Xin, W., Miao, Q., Liu, Y., Liu, R., Pun, C.M., Shi, C.: Skeleton MixFormer: multivariate topology representation for skeleton-based action recognition. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2211\u20132220 (2023)","DOI":"10.1145\/3581783.3611900"},{"key":"23_CR65","doi-asserted-by":"crossref","unstructured":"Xu, K., Ye, F., Zhong, Q., Xie, D.: Topology-aware convolutional neural network for efficient skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2866\u20132874 (2022)","DOI":"10.1609\/aaai.v36i3.20191"},{"issue":"7","key":"23_CR66","doi-asserted-by":"publisher","first-page":"1044","DOI":"10.1109\/LSP.2018.2841649","volume":"25","author":"Y Xu","year":"2018","unstructured":"Xu, Y., Cheng, J., Wang, L., Xia, H., Liu, F., Tao, D.: Ensemble one-dimensional convolution neural networks for skeleton-based action recognition. IEEE Signal Process. Lett. 25(7), 1044\u20131048 (2018)","journal-title":"IEEE Signal Process. Lett."},{"key":"23_CR67","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, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"23_CR68","doi-asserted-by":"crossref","unstructured":"Ye, F., Pu, S., Zhong, Q., Li, C., Xie, D., Tang, H.: Dynamic GCN: context-enriched topology learning for skeleton-based action recognition. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 55\u201363 (2020)","DOI":"10.1145\/3394171.3413941"},{"key":"23_CR69","doi-asserted-by":"crossref","unstructured":"Zeng, A., Sun, X., Yang, L., Zhao, N., Liu, M., Xu, Q.: Learning skeletal graph neural networks for hard 3D pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11436\u201311445 (2021)","DOI":"10.1109\/ICCV48922.2021.01124"},{"key":"23_CR70","unstructured":"Zhang, J., He, T., Sra, S., Jadbabaie, A.: Why gradient clipping accelerates training: a theoretical justification for adaptivity. arXiv preprint arXiv:1905.11881 (2019)"},{"key":"23_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., Zheng, N.: View adaptive recurrent neural networks for high performance human action recognition from skeleton data. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2117\u20132126 (2017)","DOI":"10.1109\/ICCV.2017.233"},{"key":"23_CR72","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1112\u20131121 (2020)","DOI":"10.1109\/CVPR42600.2020.00119"},{"key":"23_CR73","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wu, B., Li, W., Duan, L., Gan, C.: STST: spatial-temporal specialized transformer for skeleton-based action recognition. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3229\u20133237 (2021)","DOI":"10.1145\/3474085.3475473"},{"issue":"2","key":"23_CR74","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MMUL.2012.24","volume":"19","author":"Z Zhang","year":"2012","unstructured":"Zhang, Z.: Microsoft kinect sensor and its effect. IEEE Multimedia 19(2), 4\u201310 (2012)","journal-title":"IEEE Multimedia"},{"key":"23_CR75","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Q., Wang, Y.: Learning discriminative representations for skeleton based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10608\u201310617 (2023)","DOI":"10.1109\/CVPR52729.2023.01022"},{"key":"23_CR76","unstructured":"Zhou, Y., Li, C., Cheng, Z.Q., Geng, Y., Xie, X., Keuper, M.: Hypergraph transformer for skeleton-based action recognition. arXiv preprint arXiv:2211.09590 (2022)"},{"key":"23_CR77","doi-asserted-by":"crossref","unstructured":"Zhu, W., et al.: Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a030 (2016)","DOI":"10.1609\/aaai.v30i1.10451"}],"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\/978-3-031-72940-9_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T21:35:33Z","timestamp":1731792933000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72940-9_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,17]]},"ISBN":["9783031729393","9783031729409"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72940-9_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,17]]},"assertion":[{"value":"17 November 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"}}]}}