{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T13:50:24Z","timestamp":1761227424469,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819521005"},{"type":"electronic","value":"9789819521012"}],"license":[{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-2101-2_39","type":"book-chapter","created":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T13:27:10Z","timestamp":1761226030000},"page":"473-483","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Skeleton-Based Action Segmentation via\u00a0Multi-granularity Perception"],"prefix":"10.1007","author":[{"given":"Zhihao","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenze","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zimo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihong","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honghai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,24]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Cheng, B., et al.: Panoptic-deeplab: a simple, strong, and fast baseline for bottom-up panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12475\u201312485 (2020)","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"39_CR2","unstructured":"Ding, L., Xu, C.: TricorNet: A hybrid temporal convolutional and recurrent network for video action segmentation. arXiv preprint arXiv:1705.07818 (2017)"},{"key":"39_CR3","unstructured":"Ding, L., Xu, C.: Weakly-supervised action segmentation with iterative soft boundary assignment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6508\u20136516 (2018)"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Du, D., Su, B., Li, Y., Qi, Z., Si, L., Shan, Y.: Do we really need temporal convolutions in action segmentation? In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 1014\u20131019. IEEE (2023)","DOI":"10.1109\/ICME55011.2023.00178"},{"issue":"5","key":"39_CR5","doi-asserted-by":"publisher","first-page":"6181","DOI":"10.1007\/s11063-022-11133-9","volume":"55","author":"Z Du","year":"2023","unstructured":"Du, Z., Wang, Q.: Dilated transformer with feature aggregation module for action segmentation. Neural Process. Lett. 55(5), 6181\u20136197 (2023)","journal-title":"Neural Process. Lett."},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Gall, J.: MS-TCN: multi-stage temporal convolutional network for action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3575\u20133584 (2019)","DOI":"10.1109\/CVPR.2019.00369"},{"issue":"1","key":"39_CR7","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1109\/TETC.2022.3230912","volume":"12","author":"B Filtjens","year":"2022","unstructured":"Filtjens, B., Vanrumste, B., Slaets, P.: Skeleton-based action segmentation with multi-stage spatial-temporal graph convolutional neural networks. IEEE Trans. Emerg. Top. Comput. 12(1), 202\u2013212 (2022)","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: Cascaded boundary regression for temporal action detection. In: BMVC (2017)","DOI":"10.5244\/C.31.52"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Ishikawa, Y., Kasai, S., Aoki, Y., Kataoka, H.: Alleviating over-segmentation errors by detecting action boundaries. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2322\u20132331 (2021)","DOI":"10.1109\/WACV48630.2021.00237"},{"key":"39_CR10","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are RNNs: fast autoregressive transformers with linear attention. In: International Conference on Machine Learning, pp. 5156\u20135165. PMLR (2020)"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D.: Temporal convolutional networks for action segmentation and detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 156\u2013165 (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Lei, P., Todorovic, S.: Temporal deformable residual networks for action segmentation in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6742\u20136751 (2018)","DOI":"10.1109\/CVPR.2018.00705"},{"key":"39_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1007\/978-3-030-36718-3_40","volume-title":"Neural Information Processing","author":"L Li","year":"2019","unstructured":"Li, L., Kong, T., Sun, F., Liu, H.: Deep point-wise prediction for action temporal proposal. In: Gedeon, T., Wong, K.W., Lee, M. (eds.) ICONIP 2019. LNCS, vol. 11955, pp. 475\u2013487. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-36718-3_40"},{"issue":"06","key":"39_CR14","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.: MS-TCN++: multi-stage temporal convolutional network for action segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(06), 6647\u20136658 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Efficient two-step networks for temporal action segmentation. Neurocomputing 454, 373\u2013381 (2021)","DOI":"10.1016\/j.neucom.2021.04.121"},{"key":"39_CR16","unstructured":"Li, Y., Li, Z., Gao, S., Wang, Q., Hou, Q., Cheng, M.M.: A decoupled spatio-temporal framework for skeleton-based action segmentation. arXiv preprint arXiv:2312.05830 (2023)"},{"key":"39_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/978-981-99-8537-1_16","volume-title":"Pattern Recognition and Computer Vision","author":"T Lin","year":"2023","unstructured":"Lin, T., Chang, X., Sun, W., Zheng, W.: Prototypical transformer for weakly supervised action segmentation. In: Liu, Q., et al. (eds.) PRCV 2023. LNCS, vol. 14430, pp. 195\u2013206. Springer, Singapore (2023). https:\/\/doi.org\/10.1007\/978-981-99-8537-1_16"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Liu, C., Hu, Y., Li, Y., Song, S., Liu, J.: PKU-MMD: a large scale benchmark for skeleton-based human action understanding. In: Proceedings of the Workshop on Visual Analysis in Smart and Connected Communities, pp.\u00a01\u20138 (2017)","DOI":"10.1145\/3132734.3132739"},{"key":"39_CR20","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":"39_CR21","unstructured":"Lu, W., Chen, S.B., Ding, C.H., Tang, J., Luo, B.: LWGANet: a lightweight group attention backbone for remote sensing visual tasks. arXiv preprint arXiv:2501.10040 (2025)"},{"key":"39_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/978-3-030-58517-4_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"F Sener","year":"2020","unstructured":"Sener, F., Singhania, D., Yao, A.: Temporal aggregate representations for long-range video understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 154\u2013171. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_10"},{"issue":"2","key":"39_CR23","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1007\/s00530-022-00998-4","volume":"29","author":"X Tian","year":"2023","unstructured":"Tian, X., Jin, Y., Tang, X.: Local-global transformer neural network for temporal action segmentation. Multimedia Syst. 29(2), 615\u2013626 (2023)","journal-title":"Multimedia Syst."},{"key":"39_CR24","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.neucom.2020.03.066","volume":"407","author":"D Wang","year":"2020","unstructured":"Wang, D., Yuan, Y., Wang, Q.: Gated forward refinement network for action segmentation. Neurocomputing 407, 63\u201371 (2020)","journal-title":"Neurocomputing"},{"key":"39_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-030-58595-2_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Gao, Z., Wang, L., Li, Z., Wu, G.: Boundary-aware cascade networks for temporal action segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 34\u201351. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_3"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Learning to track for spatio-temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3164\u20133172 (2015)","DOI":"10.1109\/ICCV.2015.362"},{"key":"39_CR27","doi-asserted-by":"publisher","first-page":"103707","DOI":"10.1016\/j.cviu.2023.103707","volume":"232","author":"L Xu","year":"2023","unstructured":"Xu, L., Wang, Q., Lin, X., Yuan, L.: An efficient framework for few-shot skeleton-based temporal action segmentation. Comput. Vis. Image Underst. 232, 103707 (2023)","journal-title":"Comput. Vis. Image Underst."},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Yi, F., Wen, H., Jiang, T.: ASFormer: transformer for action segmentation. In: The British Machine Vision Conference (BMVC) (2021)","DOI":"10.5244\/C.35.49"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-2101-2_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T13:27:22Z","timestamp":1761226042000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-2101-2_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,24]]},"ISBN":["9789819521005","9789819521012"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-2101-2_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,10,24]]},"assertion":[{"value":"24 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okayama","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","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":"icira2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.icira2025.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}