{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T07:10:05Z","timestamp":1748589005429,"version":"3.41.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T00:00:00Z","timestamp":1747008000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T00:00:00Z","timestamp":1747008000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2021A1515011867"],"award-info":[{"award-number":["2021A1515011867"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s11760-025-04095-7","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T06:32:48Z","timestamp":1747031568000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Skeleton tokenized graph transformer via the Joint Bone Graph for action recognition"],"prefix":"10.1007","volume":"19","author":[{"given":"Yichang","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"4095_CR1","doi-asserted-by":"crossref","unstructured":"Lin, W., Sun, M.-T., Poovandran, R., Zhang, Z.: Human activity recognition for video surveillance. In: 2008 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 2737\u20132740 (2008). IEEE","DOI":"10.1109\/ISCAS.2008.4542023"},{"key":"4095_CR2","doi-asserted-by":"crossref","unstructured":"Rodomagoulakis, I., Kardaris, N., Pitsikalis, V., Mavroudi, E., Katsamanis, A., Tsiami, A., Maragos, P.: Multimodal human action recognition in assistive human-robot interaction. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2702\u20132706 (2016). IEEE","DOI":"10.1109\/ICASSP.2016.7472168"},{"key":"4095_CR3","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., Lin, D.: Finegym: A hierarchical video dataset for fine-grained action understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2616\u20132625 (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"4095_CR4","doi-asserted-by":"crossref","unstructured":"Nerella, S., Bandyopadhyay, S., Zhang, J., Contreras, M., Siegel, S., Bumin, A., Silva, B., Sena, J., Shickel, B., Bihorac, A., et al.: Transformers and large language models in healthcare: a review. Artific. Intell. Med., 102900 (2024)","DOI":"10.1016\/j.artmed.2024.102900"},{"key":"4095_CR5","doi-asserted-by":"crossref","unstructured":"Strohmayer, J., Lumetzberger, J., Heitzinger, T., Kampel, M.: Person-centric sensing in indoor environments. In: Scanning Technologies for Autonomous Systems, pp. 303\u2013341. Springer (2024)","DOI":"10.1007\/978-3-031-59531-8_11"},{"key":"4095_CR6","doi-asserted-by":"crossref","unstructured":"Tan, D., Tian, W., Wang, C., Chen, L., Xiong, L.: Driver distraction behavior recognition for autonomous driving: approaches, datasets and challenges. IEEE Trans. Intell. Veh. (2024)","DOI":"10.1109\/TIV.2024.3405990"},{"key":"4095_CR7","doi-asserted-by":"crossref","unstructured":"Plizzari, C., Cannici, M., Matteucci, M.: Spatial temporal transformer network for skeleton-based action recognition. In: Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10\u201315, 2021, Proceedings, Part III, pp. 694\u2013701 (2021). Springer","DOI":"10.1007\/978-3-030-68796-0_50"},{"key":"4095_CR8","doi-asserted-by":"crossref","unstructured":"Pang, Y., Ke, Q., Rahmani, H., Bailey, J., Liu, J.: Igformer: Interaction graph transformer for skeleton-based human interaction recognition. In: European Conference on Computer Vision, pp. 605\u2013622 (2022). Springer","DOI":"10.1007\/978-3-031-19806-9_35"},{"key":"4095_CR9","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":"4095_CR10","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":"4095_CR11","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":"4095_CR12","first-page":"14582","volume":"35","author":"J Kim","year":"2022","unstructured":"Kim, J., Nguyen, D., Min, S., Cho, S., Lee, M., Lee, H., Hong, S.: Pure transformers are powerful graph learners. Adv. Neural. Inf. Process. Syst. 35, 14582\u201314595 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4095_CR13","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: ACCV (2020)","DOI":"10.1007\/978-3-030-69541-5_3"},{"key":"4095_CR14","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"},{"key":"4095_CR15","unstructured":"Zhou, Y., Cheng, Z.-Q., Li, C., Fang, Y., Geng, Y., Xie, X., Keuper, M.: Hypergraph transformer for skeleton-based action recognition. arXiv preprint arXiv:2211.09590 (2022)"},{"key":"4095_CR16","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Huang, H., Wang, X., Yan, X., Xu, L.: Spatio-temporal fusion for human action recognition via joint trajectory graph. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 7579\u20137587 (2024)","DOI":"10.1609\/aaai.v38i7.28590"},{"key":"4095_CR17","doi-asserted-by":"crossref","unstructured":"Do, J., Kim, M.: Skateformer: skeletal-temporal transformer for human action recognition. In: European Conference on Computer Vision, pp. 401\u2013420 (2025). Springer","DOI":"10.1007\/978-3-031-72940-9_23"},{"key":"4095_CR18","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 (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00810"},{"issue":"8","key":"4095_CR19","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.: Graph edge convolutional neural networks for skeleton-based action recognition. IEEE Trans. Neural Netw. Learn. Syst. 31(8), 3047\u20133060 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"4095_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112319","volume":"302","author":"T Li","year":"2024","unstructured":"Li, T., Geng, P., Cai, G., Hou, X., Lu, X., Lyu, L.: Variation-aware directed graph convolutional networks for skeleton-based action recognition. Knowl.-Based Syst. 302, 112319 (2024)","journal-title":"Knowl.-Based Syst."},{"issue":"8","key":"4095_CR21","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.: Graph edge convolutional neural networks for skeleton-based action recognition. IEEE Trans. Neural Netw. Learn. Syst. 31(8), 3047\u20133060 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"4095_CR22","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"},{"issue":"10","key":"4095_CR23","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":"4095_CR24","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. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"4095_CR25","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":"4095_CR26","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":"4095_CR27","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 143\u2013152 (2020)","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"4095_CR28","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":"4095_CR29","doi-asserted-by":"crossref","unstructured":"Yang, S., Wang, X., Gao, L., Song, J.: Mke-gcn: Multi-modal knowledge embedded graph convolutional network for skeleton-based action recognition in the wild. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 01\u201306 (2022). IEEE","DOI":"10.1109\/ICME52920.2022.9859787"},{"issue":"2","key":"4095_CR30","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.1109\/TPAMI.2022.3157033","volume":"45","author":"Y-F 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":"4095_CR31","doi-asserted-by":"crossref","unstructured":"Hou, R., Li, Y., Zhang, N., Zhou, Y., Yang, X., Wang, Z.: Shifting perspective to see difference: a novel multi-view method for skeleton based action recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4987\u20134995 (2022)","DOI":"10.1145\/3503161.3548210"},{"key":"4095_CR32","doi-asserted-by":"crossref","unstructured":"Wang, X., Dai, Y., Gao, L., Song, J.: Skeleton-based action recognition via adaptive cross-form learning. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1670\u20131678 (2022)","DOI":"10.1145\/3503161.3547811"},{"key":"4095_CR33","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"},{"issue":"1","key":"4095_CR34","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/s11760-023-02747-0","volume":"18","author":"J Tang","year":"2024","unstructured":"Tang, J., Gong, S., Wang, Y., Liu, B., Du, C., Gu, B.: Beyond coordinate attention: spatial-temporal recalibration and channel scaling for skeleton-based action recognition. Signal Image Video Process. 18(1), 199\u2013206 (2024)","journal-title":"Signal Image Video Process."},{"key":"4095_CR35","doi-asserted-by":"crossref","unstructured":"Bai, R., Li, M., Meng, B., Li, F., Jiang, M., Ren, J., Sun, D.: Hierarchical graph convolutional skeleton transformer for action recognition. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 01\u201306 (2022). IEEE","DOI":"10.1109\/ICME52920.2022.9859781"},{"key":"4095_CR36","doi-asserted-by":"crossref","unstructured":"Gao, Z., Wang, P., Lv, P., Jiang, X., Liu, Q., Wang, P., Xu, M., Li, W.: Focal and global spatial-temporal transformer for skeleton-based action recognition. In: Proceedings of the Asian Conference on Computer Vision, pp. 382\u2013398 (2022)","DOI":"10.1007\/978-3-031-26316-3_10"},{"key":"4095_CR37","doi-asserted-by":"crossref","unstructured":"Liu, H., Liu, Y., Chen, Y., Yuan, C., Li, B., Hu, W.: Transkeleton: Hierarchical spatial-temporal transformer for skeleton-based action recognition. IEEE Transactions on Circuits and Systems for Video Technology (2023)","DOI":"10.1109\/TCSVT.2023.3240472"},{"key":"4095_CR38","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4095_CR39","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"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04095-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04095-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04095-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T06:39:31Z","timestamp":1748587171000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04095-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,12]]},"references-count":39,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["4095"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04095-7","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2025,5,12]]},"assertion":[{"value":"22 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"575"}}