{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T23:52:10Z","timestamp":1781826730723,"version":"3.54.5"},"reference-count":100,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1007\/s11263-026-02797-0","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T02:52:43Z","timestamp":1775530363000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DeST: A Decoupled Spatio-Temporal Framework for Action\u00a0Segmentation"],"prefix":"10.1007","volume":"134","author":[{"given":"Yunheng","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong-Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanghua","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qilong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8388-8708","authenticated-orcid":false,"given":"Qibin","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"key":"2797_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, H., & Lee, D. (2021). Refining action segmentation with hierarchical video representations. In: Int. Conf. Comput. Vis. (ICCV). pp. 16302\u201316310","DOI":"10.1109\/ICCV48922.2021.01599"},{"key":"2797_CR2","doi-asserted-by":"crossref","unstructured":"Aksan, E., Kaufmann, M., Cao, P., & Hilliges, O. (2021). A spatio-temporal transformer for 3d human motion prediction. In: 3DV. pp. 565\u2013574. IEEE","DOI":"10.1109\/3DV53792.2021.00066"},{"key":"2797_CR3","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., & Schmid, C. (2021). Vivit: A video vision transformer. In: Int. Conf. Comput. Vis. (ICCV). pp. 6836\u20136846","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"2797_CR4","doi-asserted-by":"crossref","unstructured":"Behrmann, N., Golestaneh, S.A., Kolter, Z., Gall, J., & Noroozi, M. (2022). Unified fully and timestamp supervised temporal action segmentation via sequence to sequence translation. In: Eur. Conf. Comput. Vis. (ECCV). pp. 52\u201368. Springer","DOI":"10.1007\/978-3-031-19833-5_4"},{"issue":"4","key":"2797_CR5","first-page":"13","volume":"5","author":"A Biswas","year":"2014","unstructured":"Biswas, A., Dutta, S., Dey, N., & Azar, A. T. (2014). A kinect-less augmented reality approach to real-time tag-less virtual trial room simulation. IJSSMET, 5(4), 13\u201328.","journal-title":"IJSSMET"},{"key":"2797_CR6","doi-asserted-by":"crossref","unstructured":"Bo, D., Wang, X., Shi, C., & Shen, H. (2021). Beyond low-frequency information in graph convolutional networks. In: AAAI Conf. Artif. Intell. (AAAI). pp. 3950\u20133957","DOI":"10.1609\/aaai.v35i5.16514"},{"issue":"11","key":"2797_CR7","doi-asserted-by":"publisher","first-page":"3247","DOI":"10.1109\/TCSVT.2018.2879913","volume":"29","author":"C Cao","year":"2018","unstructured":"Cao, C., Lan, C., Zhang, Y., Zeng, W., Lu, H., & Zhang, Y. (2018). Skeleton-based action recognition with gated convolutional neural networks. IEEE Trans. Circ. Syst. Video Technol. (TCSVT), 29(11), 3247\u20133257.","journal-title":"IEEE Trans. Circ. Syst. Video Technol. (TCSVT)"},{"key":"2797_CR8","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., & Sheikh, Y. (July 2017). Realtime multi-person 2d pose estimation using part affinity fields. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR)","DOI":"10.1109\/CVPR.2017.143"},{"key":"2797_CR9","doi-asserted-by":"publisher","first-page":"27309","DOI":"10.1007\/s11042-019-07827-3","volume":"78","author":"F Carrara","year":"2019","unstructured":"Carrara, F., Elias, P., Sedmidubsky, J., & Zezula, P. (2019). Lstm-based real-time action detection and prediction in human motion streams. Multimed Tools Appl., 78, 27309\u201327331.","journal-title":"Multimed Tools Appl."},{"key":"2797_CR10","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (2017). Quo vadis, action recognition? a new model and the kinetics dataset. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"2797_CR11","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (July 2017). Quo vadis, action recognition? a new model and the kinetics dataset. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR)","DOI":"10.1109\/CVPR.2017.502"},{"key":"2797_CR12","doi-asserted-by":"crossref","unstructured":"Chen, M.H., Li, B., Bao, Y., AlRegib, G., & Kira, Z. (June 2020). Action segmentation with joint self-supervised temporal domain adaptation. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR)","DOI":"10.1109\/CVPR42600.2020.00947"},{"key":"2797_CR13","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: Eur. Conf. Comput. Vis. (ECCV). pp. 185\u2013202","DOI":"10.1007\/978-3-031-19809-0_11"},{"key":"2797_CR14","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., & Hu, W. (October 2021). Channel-wise topology refinement graph convolution for skeleton-based action recognition. In: Int. Conf. Comput. Vis. (ICCV). pp. 13359\u201313368","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"2797_CR15","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, S., Yang, B., Li, Q., & Liu, H. (2021). Multi-scale spatial temporal graph convolutional network for skeleton-based action recognition. In: AAAI Conf. Artif. Intell. (AAAI). pp. 1113\u20131122","DOI":"10.1609\/aaai.v35i2.16197"},{"key":"2797_CR16","doi-asserted-by":"crossref","unstructured":"Cheng, K., Zhang, Y., Cao, C., Shi, L., Cheng, J., & Lu, H. (2020). Decoupling gcn with dropgraph module for skeleton-based action recognition. In: Eur. Conf. Comput. Vis. (ECCV). pp. 536\u2013553. Springer","DOI":"10.1007\/978-3-030-58586-0_32"},{"key":"2797_CR17","doi-asserted-by":"publisher","first-page":"7333","DOI":"10.1109\/TIP.2021.3104182","volume":"30","author":"K Cheng","year":"2021","unstructured":"Cheng, K., Zhang, Y., He, X., Cheng, J., & Lu, H. (2021). Extremely lightweight skeleton-based action recognition with shiftgcn++. IEEE Trans. Image Process. (TIP), 30, 7333\u20137348.","journal-title":"IEEE Trans. Image Process. (TIP)"},{"key":"2797_CR18","doi-asserted-by":"crossref","unstructured":"Cui, Q., Sun, H., & Yang, F. (2020). Learning dynamic relationships for 3d human motion prediction. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 6519\u20136527","DOI":"10.1109\/CVPR42600.2020.00655"},{"key":"2797_CR19","doi-asserted-by":"crossref","unstructured":"Dang, L., Nie, Y., Long, C., Zhang, Q., & Li, G. (October 2021). Msr-gcn: Multi-scale residual graph convolution networks for human motion prediction. In: Int. Conf. Comput. Vis. (ICCV). pp. 11467\u201311476","DOI":"10.1109\/ICCV48922.2021.01127"},{"key":"2797_CR20","unstructured":"Ding, L., & Xu, C. (2017). Tricornet: A hybrid temporal convolutional and recurrent network for video action segmentation. arXiv:1705.07818"},{"key":"2797_CR21","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S., et\u00a0al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929"},{"key":"2797_CR22","doi-asserted-by":"crossref","unstructured":"Bahrami, E., & Gianpiero\u00a0Francesca, J.G. (2023). How much temporal long-term context is needed for action segmentation? In: Int. Conf. Comput. Vis. (ICCV)","DOI":"10.1109\/ICCV51070.2023.00950"},{"key":"2797_CR23","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., & Gall, J. (2019). Ms-tcn: Multi-stage temporal convolutional network for action segmentation. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 3575\u20133584","DOI":"10.1109\/CVPR.2019.00369"},{"key":"2797_CR24","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.gaitpost.2020.05.026","volume":"80","author":"B Filtjens","year":"2020","unstructured":"Filtjens, B., Nieuwboer, A., D\u2019cruz, N., Spildooren, J., Slaets, P., & Vanrumste, B. (2020). A data-driven approach for detecting gait events during turning in people with parkinson\u2019s disease and freezing of gait. Gait & Posture, 80, 130\u2013136.","journal-title":"Gait & Posture"},{"key":"2797_CR25","volume-title":"Skeleton-based action segmentation with multi-stage spatial-temporal graph convolutional neural networks","author":"B Filtjens","year":"2022","unstructured":"Filtjens, B., Vanrumste, B., & Slaets, P. (2022). Skeleton-based action segmentation with multi-stage spatial-temporal graph convolutional neural networks. Com: IEEE Trans. Emerg. Top."},{"issue":"2","key":"2797_CR26","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"SH Gao","year":"2019","unstructured":"Gao, S. H., Cheng, M. M., Zhao, K., Zhang, X. Y., Yang, M. H., & Torr, P. (2019). Res2net: A new multi-scale backbone architecture. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 43(2), 652\u2013662.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"2797_CR27","doi-asserted-by":"crossref","unstructured":"Gao, S.H., Han, Q., Li, Z.Y., Peng, P., Wang, L., & Cheng, M.M. (June 2021). Global2local: Efficient structure search for video action segmentation. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 16805\u201316814","DOI":"10.1109\/CVPR46437.2021.01653"},{"issue":"3","key":"2797_CR28","first-page":"2984","volume":"45","author":"S Gao","year":"2022","unstructured":"Gao, S., Li, Z. Y., Han, Q., Cheng, M. M., & Wang, L. (2022). Rf-next: Efficient receptive field search for convolutional neural networks. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 45(3), 2984\u20133002.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"issue":"5\u20136","key":"2797_CR29","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","volume":"18","author":"A Graves","year":"2005","unstructured":"Graves, A., & Schmidhuber, J. (2005). Framewise phoneme classification with bidirectional lstm and other neural network architectures. Neural networks, 18(5\u20136), 602\u2013610.","journal-title":"Neural networks"},{"key":"2797_CR30","doi-asserted-by":"publisher","first-page":"2263","DOI":"10.1109\/TIP.2021.3051495","volume":"30","author":"X Hao","year":"2021","unstructured":"Hao, X., Li, J., Guo, Y., Jiang, T., & Yu, M. (2021). Hypergraph neural network for skeleton-based action recognition. IEEE Trans. Image Process. (TIP), 30, 2263\u20132275.","journal-title":"IEEE Trans. Image Process. (TIP)"},{"key":"2797_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"9","key":"2797_CR32","doi-asserted-by":"publisher","first-page":"2207","DOI":"10.1109\/TMM.2019.2953325","volume":"22","author":"G Hu","year":"2019","unstructured":"Hu, G., Cui, B., & Yu, S. (2019). Joint learning in the spatio-temporal and frequency domains for skeleton-based action recognition. IEEE Trans. Multimedia (TMM), 22(9), 2207\u20132220.","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"2797_CR33","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., & Weinberger, K.Q. (2017). Densely connected convolutional networks. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"2797_CR34","doi-asserted-by":"crossref","unstructured":"Ishikawa, Y., Kasai, S., Aoki, Y., & Kataoka, H. (2021). Alleviating over-segmentation errors by detecting action boundaries. In: WACV. pp. 2322\u20132331","DOI":"10.1109\/WACV48630.2021.00237"},{"key":"2797_CR35","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., & Fleuret, F. (13\u201318 Jul 2020). Transformers are RNNs: Fast autoregressive transformers with linear attention. In: III, H.D., Singh, A. (eds.) Int. Conf. Mach. Learn. (ICML). vol.\u00a0119, pp. 5156\u20135165. PMLR"},{"key":"2797_CR36","doi-asserted-by":"crossref","unstructured":"Kenney, J., Buckley, T., & Brock, O. (2009). Interactive segmentation for manipulation in unstructured environments. In: ICRA. pp. 1377\u20131382. IEEE","DOI":"10.1109\/ROBOT.2009.5152393"},{"key":"2797_CR37","doi-asserted-by":"crossref","unstructured":"Kidzi\u0144ski, \u0141, Delp, S., & Schwartz, M. (2019). Automatic real-time gait event detection in children using deep neural networks. PLoS ONE,14(1), Article e0211466.","DOI":"10.1371\/journal.pone.0211466"},{"issue":"11","key":"2797_CR38","doi-asserted-by":"publisher","first-page":"4394","DOI":"10.1109\/TCSVT.2021.3050807","volume":"31","author":"J Kong","year":"2021","unstructured":"Kong, J., Deng, H., & Jiang, M. (2021). Symmetrical enhanced fusion network for skeleton-based action recognition. IEEE Trans. Circ. Syst. Video Technol. (TCSVT), 31(11), 4394\u20134408.","journal-title":"IEEE Trans. Circ. Syst. Video Technol. (TCSVT)"},{"key":"2797_CR39","doi-asserted-by":"crossref","unstructured":"Korban, M., & Li, X. (2023). Semantics-enhanced early action detection using dynamic dilated convolution. Pattern Recogn.,140, Article 109595.","DOI":"10.1016\/j.patcog.2023.109595"},{"key":"2797_CR40","doi-asserted-by":"crossref","unstructured":"Lea, C., Flynn, M.D., Vidal, R., Reiter, A., & Hager, G.D. (2017). Temporal convolutional networks for action segmentation and detection. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 156\u2013165","DOI":"10.1109\/CVPR.2017.113"},{"key":"2797_CR41","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 Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 4741\u20134750","DOI":"10.1109\/CVPR46437.2021.00471"},{"issue":"6","key":"2797_CR42","doi-asserted-by":"publisher","first-page":"3316","DOI":"10.1109\/TPAMI.2021.3053765","volume":"44","author":"M Li","year":"2021","unstructured":"Li, M., Chen, S., Chen, X., Zhang, Y., Wang, Y., & Tian, Q. (2021). Symbiotic graph neural networks for 3d skeleton-based human action recognition and motion prediction. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 44(6), 3316\u20133333.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"2797_CR43","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, S., Zhao, Y., Zhang, Y., Wang, Y., & Tian, Q. (June 2020). Dynamic multiscale graph neural networks for 3d skeleton based human motion prediction. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR)","DOI":"10.1109\/CVPR42600.2020.00029"},{"key":"2797_CR44","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, L., Duan, Y., Hu, Z., Feng, J., Zhou, J., & Lu, J. (June 2022). Bridge-prompt: Towards ordinal action understanding in instructional videos. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR)","DOI":"10.1109\/CVPR52688.2022.01926"},{"issue":"6","key":"2797_CR45","doi-asserted-by":"publisher","first-page":"6647","DOI":"10.1109\/TPAMI.2020.3021756","volume":"45","author":"S Li","year":"2023","unstructured":"Li, S., Farha, Y. A., Liu, Y., Cheng, M. M., & Gall, J. (2023). Ms-tcn++: Multi-stage temporal convolutional network for action segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 45(6), 6647\u20136658.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"2797_CR46","doi-asserted-by":"crossref","unstructured":"Li, S., He, X., Song, W., Hao, A., & Qin, H. (2023). Graph diffusion convolutional network for skeleton based semantic recognition of two-person actions. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)","DOI":"10.1109\/TPAMI.2023.3238411"},{"key":"2797_CR47","doi-asserted-by":"crossref","unstructured":"Li, Y.H., Liu, K.Y., Liu, S.L., Feng, L., & Qiao, H. (2023). Involving distinguished temporal graph convolutional networks for skeleton-based temporal action segmentation. IEEE Trans. Circ. Syst. Video Technol. (TCSVT)","DOI":"10.1109\/TCSVT.2023.3285416"},{"key":"2797_CR48","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1016\/j.neucom.2021.04.121","volume":"454","author":"Y Li","year":"2021","unstructured":"Li, Y., Dong, Z., Liu, K., Feng, L., Hu, L., Zhu, J., Xu, L., Liu, S., et al. (2021). Efficient two-step networks for temporal action segmentation. Neurocomputing, 454, 373\u2013381.","journal-title":"Neurocomputing"},{"key":"2797_CR49","doi-asserted-by":"crossref","unstructured":"Liu, C., Hu, Y., Li, Y., Song, S., & Liu, J. (2017). Pku-mmd: A large scale benchmark for skeleton-based human action understanding. In: ACM VASCCW. pp.\u00a01\u20138","DOI":"10.1145\/3132734.3132739"},{"key":"2797_CR50","doi-asserted-by":"crossref","unstructured":"Liu, D., Li, Q., Dinh, A.D., Jiang, T., Shah, M., & Xu, C. (2023). Diffusion action segmentation. In: Int. Conf. Comput. Vis. (ICCV)","DOI":"10.1109\/ICCV51070.2023.00930"},{"key":"2797_CR51","volume-title":"Temporal decoupling graph convolutional network for skeleton-based gesture recognition","author":"J Liu","year":"2023","unstructured":"Liu, J., Wang, X., Wang, C., Gao, Y., & Liu, M. (2023). Temporal decoupling graph convolutional network for skeleton-based gesture recognition. Multimedia (TMM): IEEE Trans."},{"key":"2797_CR52","doi-asserted-by":"publisher","first-page":"1883","DOI":"10.1109\/LSP.2022.3199670","volume":"29","author":"K Liu","year":"2022","unstructured":"Liu, K., Li, Y., Xu, Y., Liu, S., & Liu, S. (2022). Spatial focus attention for fine-grained skeleton-based action tasks. IEEE Signal Process. Let. (SPL), 29, 1883\u20131887.","journal-title":"IEEE Signal Process. Let. (SPL)"},{"key":"2797_CR53","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.patcog.2017.02.030","volume":"68","author":"M Liu","year":"2017","unstructured":"Liu, M., Liu, H., & Chen, C. (2017). Enhanced skeleton visualization for view invariant human action recognition. Pattern Recogn., 68, 346\u2013362.","journal-title":"Pattern Recogn."},{"key":"2797_CR54","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhang, A., Li, Y., Zhou, J., Xu, L., Dong, Z., & Zhang, R. (2021). Temporal segmentation of fine-grained semantic action: A motion-centered figure skating dataset. In: AAAI Conf. Artif. Intell. (AAAI). pp. 2163\u20132171","DOI":"10.1609\/aaai.v35i3.16314"},{"key":"2797_CR55","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., & Hu, H. (2022). Video swin transformer. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 3202\u20133211","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"2797_CR56","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, H., Chen, Z., Wang, Z., & Ouyang, W. (June 2020). Disentangling and unifying graph convolutions for skeleton-based action recognition. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR)","DOI":"10.1109\/CVPR42600.2020.00022"},{"issue":"4","key":"2797_CR57","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1111\/mice.12419","volume":"34","author":"X Luo","year":"2019","unstructured":"Luo, X., Li, H., Yang, X., Yu, Y., & Cao, D. (2019). Capturing and understanding workers\u2019 activities in far-field surveillance videos with deep action recognition and bayesian nonparametric learning. Comput-aided Civ. Inf., 34(4), 333\u2013351.","journal-title":"Comput-aided Civ. Inf."},{"key":"2797_CR58","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: Int. Conf. Comput. Vis. (ICCV). pp. 10181\u201310191","DOI":"10.1109\/ICCV51070.2023.00934"},{"key":"2797_CR59","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: Eur. Conf. Comput. Vis. (ECCV). pp. 734\u2013752","DOI":"10.1007\/978-3-031-20062-5_42"},{"issue":"15","key":"2797_CR60","doi-asserted-by":"publisher","first-page":"4083","DOI":"10.3390\/s20154083","volume":"20","author":"F Niemann","year":"2020","unstructured":"Niemann, F., Reining, C., Moya Rueda, F., Nair, N. R., Steffens, J. A., Fink, G. A., & Ten Hompel, M. (2020). Lara: Creating a dataset for human activity recognition in logistics using semantic attributes. Sensors, 20(15), 4083.","journal-title":"Sensors"},{"key":"2797_CR61","volume-title":"Action points: A representation for low-latency online human action recognition","author":"S Nowozin","year":"2012","unstructured":"Nowozin, S., & Shotton, J. (2012). Action points: A representation for low-latency online human action recognition. Microsoft Research Cambridge: Tech. Rep."},{"key":"2797_CR62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3239751","volume-title":"Skeleton-based action recognition through contrasting two-stream spatial-temporal networks","author":"C Pang","year":"2023","unstructured":"Pang, C., Lu, X., & Lyu, L. (2023). Skeleton-based action recognition through contrasting two-stream spatial-temporal networks. Multimedia (TMM): IEEE Trans."},{"key":"2797_CR63","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., & Lerer, A. (2017). Automatic differentiation in pytorch. NeurIPSW"},{"key":"2797_CR64","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., & Antiga, L., et\u00a0al. (2019). Pytorch: An imperative style, high-performance deep learning library. Annu. Conf. Neur. Inform. Process. Syst. (NeurIPS) 32"},{"key":"2797_CR65","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 Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 1010\u20131019","DOI":"10.1109\/CVPR.2016.115"},{"key":"2797_CR66","doi-asserted-by":"crossref","unstructured":"Sharaf, A., Torki, M., Hussein, M.E., & El-Saban, M. (2015). Real-time multi-scale action detection from 3d skeleton data. In: WACV. pp. 998\u20131005. IEEE","DOI":"10.1109\/WACV.2015.138"},{"key":"2797_CR67","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., & Lu, H. (June 2019). Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"2797_CR68","doi-asserted-by":"publisher","first-page":"9532","DOI":"10.1109\/TIP.2020.3028207","volume":"29","author":"L Shi","year":"2020","unstructured":"Shi, L., Zhang, Y., Cheng, J., & Lu, H. (2020). Skeleton-based action recognition with multi-stream adaptive graph convolutional networks. IEEE Trans. Image Process. (TIP), 29, 9532\u20139545.","journal-title":"IEEE Trans. Image Process. (TIP)"},{"key":"2797_CR69","doi-asserted-by":"crossref","unstructured":"Siam, M., Jiang, C., Lu, S., Petrich, L., Gamal, M., Elhoseiny, M., & Jagersand, M. (2019). Video object segmentation using teacher-student adaptation in a human robot interaction (hri) setting. In: ICRA. pp. 50\u201356. IEEE","DOI":"10.1109\/ICRA.2019.8794254"},{"key":"2797_CR70","unstructured":"Simonyan, K., & Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. Annu. Conf. Neur. Inform. Process. Syst. (NeurIPS) 27"},{"key":"2797_CR71","doi-asserted-by":"crossref","unstructured":"Singh, B., Marks, T.K., Jones, M., Tuzel, O., & Shao, M. (June 2016). A multi-stream bi-directional recurrent neural network for fine-grained action detection. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR)","DOI":"10.1109\/CVPR.2016.216"},{"key":"2797_CR72","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.autcon.2018.11.033","volume":"99","author":"H Son","year":"2019","unstructured":"Son, H., Choi, H., Seong, H., & Kim, C. (2019). Detection of construction workers under varying poses and changing background in image sequences via very deep residual networks. Automat. Constr., 99, 27\u201338.","journal-title":"Automat. Constr."},{"issue":"5","key":"2797_CR73","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TCSVT.2020.3015051","volume":"31","author":"YF Song","year":"2020","unstructured":"Song, Y. F., Zhang, Z., Shan, C., & Wang, L. (2020). Richly activated graph convolutional network for robust skeleton-based action recognition. IEEE Trans. Circ. Syst. Video Technol. (TCSVT), 31(5), 1915\u20131925.","journal-title":"IEEE Trans. Circ. Syst. Video Technol. (TCSVT)"},{"issue":"2","key":"2797_CR74","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. (2022). Constructing stronger and faster baselines for skeleton-based action recognition. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 45(2), 1474\u20131488.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"2797_CR75","doi-asserted-by":"crossref","unstructured":"Su, Y., Lin, G., & Wu, Q. (October 2021). Self-supervised 3D skeleton action representation learning with motion consistency and continuity. In: Int. Conf. Comput. Vis. (ICCV). pp. 13328\u201313338","DOI":"10.1109\/ICCV48922.2021.01308"},{"issue":"4","key":"2797_CR76","first-page":"1","volume":"8","author":"M Sudha","year":"2017","unstructured":"Sudha, M., Sriraghav, K., Jacob, S. G., Manisha, S., et al. (2017). Approaches and applications of virtual reality and gesture recognition: A review. Int. Joint Conf. Artif. Intell. (IJCAI), 8(4), 1\u201318.","journal-title":"Int. Joint Conf. Artif. Intell. (IJCAI)"},{"key":"2797_CR77","doi-asserted-by":"crossref","unstructured":"Thoker, F.M., Doughty, H., & Snoek, C.G. (2021). Skeleton-contrastive 3D action representation learning. In: ACM Int. Conf. Multimedia (ACM MM). pp. 1655\u20131663","DOI":"10.1145\/3474085.3475307"},{"key":"2797_CR78","doi-asserted-by":"crossref","unstructured":"Tian, X., Jin, Y., Zhang, Z., Liu, P. & Tang, X. (2023). Stga-net: Spatial-temporal graph attention network for skeleton-based temporal action segmentation. In: ICMEW. pp. 218\u2013223. IEEE","DOI":"10.1109\/ICMEW59549.2023.00044"},{"key":"2797_CR79","unstructured":"Tianyu, G., Hong, L., Zhan, C., Mengyuan, L., Tao, W., & Runwei, D. (2022). Contrastive learning from extremely augmented skeleton sequences for self-supervised action recognition. In: AAAI Conf. Artif. Intell. (AAAI)"},{"key":"2797_CR80","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. In: Annu. Conf. Neur. Inform. Process. Syst. (NeurIPS). pp. 5998\u20136008"},{"issue":"9","key":"2797_CR81","doi-asserted-by":"publisher","first-page":"4382","DOI":"10.1109\/TIP.2018.2837386","volume":"27","author":"H Wang","year":"2018","unstructured":"Wang, H., & Wang, L. (2018). Beyond joints: Learning representations from primitive geometries for skeleton-based action recognition and detection. IEEE Trans. Image Process. (TIP), 27(9), 4382\u20134394.","journal-title":"IEEE Trans. Image Process. (TIP)"},{"key":"2797_CR82","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, B., Zhao, Z., Tong, Z., He, Y., Wang, Y., Wang, Y., & Qiao, Y. (June 2023). Videomae v2: Scaling video masked autoencoders with dual masking. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 14549\u201314560","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"2797_CR83","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, W., Li, W., & Van\u00a0Gool, L. (2018). Appearance-and-relation networks for video classification. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 1430\u20131439","DOI":"10.1109\/CVPR.2018.00155"},{"key":"2797_CR84","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., & Tang, X. (2015). Action recognition with trajectory-pooled deep-convolutional descriptors. In: IEEE Conf. Comput. Vis. Pattern Recog. (CVPR). pp. 4305\u20134314","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"2797_CR85","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Van\u00a0Gool, L. (2016). Temporal segment networks: Towards good practices for deep action recognition. In: Eur. Conf. Comput. Vis. (ECCV). pp. 20\u201336. Springer","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"2797_CR86","unstructured":"Wang, M., Ni, B., & Yang, X. (2020). Learning multi-view interactional skeleton graph for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"2797_CR87","doi-asserted-by":"crossref","unstructured":"Wang, Z.Z., Gao, Z.T., Wang, L.M., Li, Z.F., & Wu, G.S. (2020). Boundary-aware cascade networks for temporal action segmentation. In: Eur. Conf. Comput. Vis. (ECCV). Springer","DOI":"10.1007\/978-3-030-58595-2_3"},{"key":"2797_CR88","doi-asserted-by":"crossref","unstructured":"Wu, W., Hua, Y., Zheng, C., Wu, S., Chen, C., & Lu, A. (2023). SkeletonMAE: Spatial-temporal masked autoencoders for self-supervised skeleton action recognition. In: ICMEW. pp. 224\u2013229","DOI":"10.1109\/ICMEW59549.2023.00045"},{"key":"2797_CR89","doi-asserted-by":"crossref","unstructured":"Xu, B., Shu, X., Zhang, J., Dai, G., & Song, Y. (2023). Spatiotemporal decouple-and-squeeze contrastive learning for semisupervised skeleton-based action recognition. IEEE Trans. Neur. Net. Learn. Syst. (TNNLS)","DOI":"10.1109\/TNNLS.2023.3247103"},{"key":"2797_CR90","doi-asserted-by":"crossref","unstructured":"Xu, L., Wang, Q., Lin, X., & Yuan, L. (2023). An efficient framework for few-shot skeleton-based temporal action segmentation. Comput. Vis. Image Und.,232, Article 103707.","DOI":"10.1016\/j.cviu.2023.103707"},{"key":"2797_CR91","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., & Lin, D. (2018). Spatial temporal graph convolutional networks for skeleton-based action recognition. In: AAAI Conf. Artif. Intell. (AAAI)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"2797_CR92","doi-asserted-by":"crossref","unstructured":"Yang, D., Wang, Y., Dantcheva, A., Garattoni, L., Francesca, G., & Br\u00e9mond, F. (2024). ViA: View-invariant skeleton action representation learning via motion retargeting. Int. J. Comput. Vis. (IJCV) pp. 1\u201316","DOI":"10.1007\/s11263-023-01967-8"},{"key":"2797_CR93","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1109\/TIP.2021.3129117","volume":"31","author":"H Yang","year":"2021","unstructured":"Yang, H., Yan, D., Zhang, L., Sun, Y., Li, D., & Maybank, S. J. (2021). Feedback graph convolutional network for skeleton-based action recognition. IEEE Trans. Image Process. (TIP), 31, 164\u2013175.","journal-title":"IEEE Trans. Image Process. (TIP)"},{"key":"2797_CR94","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: Int. Conf. Comput. Vis. (ICCV). pp. 13423\u201313433","DOI":"10.1109\/ICCV48922.2021.01317"},{"key":"2797_CR95","doi-asserted-by":"crossref","unstructured":"Yi, F., Wen, H., & Jiang, T. (2021). Asformer: Transformer for action segmentation. In: Brit. Mach. Vis. Conf. (BMVC)","DOI":"10.5244\/C.35.49"},{"key":"2797_CR96","doi-asserted-by":"crossref","unstructured":"Yu, H., Fan, X., Hou, Y., Pei, W., Ge, H., Yang, X., Zhou, D., Zhang, Q., & Zhang, M. (2023). Towards realistic 3d human motion prediction with a spatio-temporal cross-transformer approach. IEEE Trans. Circ. Syst. Video Technol. (TCSVT)","DOI":"10.1109\/TCSVT.2023.3255186"},{"key":"2797_CR97","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hou, Y., Zhang, W., & Li, W. (2022). Contrastive positive mining for unsupervised 3D action representation learning. In: Eur. Conf. Comput. Vis. (ECCV). pp. 36\u201351","DOI":"10.1007\/978-3-031-19772-7_3"},{"issue":"8","key":"2797_CR98","doi-asserted-by":"publisher","first-page":"1963","DOI":"10.1109\/TPAMI.2019.2896631","volume":"41","author":"P Zhang","year":"2019","unstructured":"Zhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., & Zheng, N. (2019). View adaptive neural networks for high performance skeleton-based human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 41(8), 1963\u20131978.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"issue":"8","key":"2797_CR99","doi-asserted-by":"publisher","first-page":"3047","DOI":"10.1109\/TNNLS.2019.2935173","volume":"31","author":"X Zhang","year":"2019","unstructured":"Zhang, X., Xu, C., Tian, X., & Tao, D. (2019). Graph edge convolutional neural networks for skeleton-based action recognition. IEEE Trans. Neur. Net. Learn. Syst. (TNNLS), 31(8), 3047\u20133060.","journal-title":"IEEE Trans. Neur. Net. Learn. Syst. (TNNLS)"},{"key":"2797_CR100","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1109\/TIP.2022.3230249","volume":"32","author":"Y Zhu","year":"2022","unstructured":"Zhu, Y., Shuai, H., Liu, G., & Liu, Q. (2022). Multilevel spatial-temporal excited graph network for skeleton-based action recognition. IEEE Trans. Image Process. (TIP), 32, 496\u2013508.","journal-title":"IEEE Trans. Image Process. (TIP)"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02797-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02797-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02797-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T23:07:41Z","timestamp":1781824061000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02797-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,7]]},"references-count":100,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["2797"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02797-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,7]]},"assertion":[{"value":"7 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"204"}}