{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:47:35Z","timestamp":1777567655897,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819985487","type":"print"},{"value":"9789819985494","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8549-4_3","type":"book-chapter","created":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T18:01:32Z","timestamp":1703440892000},"page":"28-39","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Hierarchical Spatial-Temporal Network for\u00a0Skeleton-Based Temporal Action Segmentation"],"prefix":"10.1007","author":[{"given":"Chenwei","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Talas","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minjie","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenglan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Chen, H.T., Chen, H.S., Lee, S.Y.: Physics-based ball tracking in volleyball videos with its applications to set type recognition and action detection. In: 2007 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2007), vol. 1, pp. I\u20131097. IEEE (2007)","DOI":"10.1109\/ICASSP.2007.366103"},{"key":"3_CR2","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"},{"issue":"8","key":"3_CR3","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/TPAMI.2000.868676","volume":"22","author":"RT Collins","year":"2000","unstructured":"Collins, R.T., Lipton, A.J., Kanade, T.: Introduction to the special section on video surveillance. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 745\u2013746 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1110\u20131118 (2015)","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"3_CR5","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"},{"key":"3_CR6","doi-asserted-by":"crossref","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. 1\u201311 (2022)","DOI":"10.1109\/TETC.2022.3230912"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3_CR8","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"},{"issue":"7","key":"3_CR9","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1109\/TCSVT.2019.2914137","volume":"30","author":"X Jiang","year":"2019","unstructured":"Jiang, X., Xu, K., Sun, T.: Action recognition scheme based on skeleton representation with DS-LSTM network. IEEE Trans. Circuits Syst. Video Technol. 30(7), 2129\u20132140 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3_CR10","unstructured":"Joze, H.R.V., Shaban, A., Iuzzolino, M.L., Koishida, K.: MMTM: multimodal transfer module for CNN fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13289\u201313299 (2020)"},{"key":"3_CR11","unstructured":"Karaman, S., Seidenari, L., Del Bimbo, A.: Fast saliency based pooling of fisher encoded dense trajectories. In: ECCV THUMOS Workshop, p. 5 (2014)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Kim, T.S., Reiter, A.: Interpretable 3d human action analysis with temporal convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1623\u20131631. IEEE (2017)","DOI":"10.1109\/CVPRW.2017.207"},{"issue":"13","key":"3_CR13","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1163\/156855307782148578","volume":"21","author":"V Kr\u00fcger","year":"2007","unstructured":"Kr\u00fcger, V., Kragic, D., Ude, A., Geib, C.: The meaning of action: a review on action recognition and mapping. Adv. Robot. 21(13), 1473\u20131501 (2007)","journal-title":"Adv. Robot."},{"key":"3_CR14","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":"3_CR15","doi-asserted-by":"crossref","unstructured":"Li, C., Zhong, Q., Xie, D., Pu, S.: Skeleton-based action recognition with convolutional neural networks. In: 2017 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pp. 597\u2013600. IEEE (2017)","DOI":"10.1109\/ICMEW.2017.8026285"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Liu, C., Hu, Y., Li, Y., Song, S., Liu, J.: PKU-MMD: a large scale benchmark for continuous multi-modal human action understanding. arXiv preprint arXiv:1703.07475 (2017)","DOI":"10.1145\/3132734.3132739"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.:: Temporal segmentation of fine-gained semantic action: a motion-centered figure skating dataset. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2163\u20132171 (2021)","DOI":"10.1609\/aaai.v35i3.16314"},{"issue":"6","key":"3_CR18","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/MSP.2017.2738401","volume":"34","author":"D Ramachandram","year":"2017","unstructured":"Ramachandram, D., Taylor, G.W.: Deep multimodal learning: a survey on recent advances and trends. IEEE Signal Process. Mag. 34(6), 96\u2013108 (2017)","journal-title":"IEEE Signal Process. Mag."},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Amin, S., Andriluka, M., Schiele, B.: A database for fine grained activity detection of cooking activities. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1194\u20131201. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"3_CR20","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":"3_CR21","doi-asserted-by":"crossref","unstructured":"Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: Proceedings of the AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"3_CR22","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"},{"key":"3_CR23","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-030-58595-2_3"},{"key":"3_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, pp. 7444\u20137452 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"3_CR25","unstructured":"Yi, F., Wen, H., Jiang, T.: Asformer: transformer for action segmentation, p. 236 (2021)"},{"key":"3_CR26","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":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8549-4_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T20:06:46Z","timestamp":1730923606000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8549-4_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"ISBN":["9789819985487","9789819985494"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8549-4_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,25]]},"assertion":[{"value":"25 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"532","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,78","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,69","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}