{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:04:56Z","timestamp":1783530296183,"version":"3.55.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197710","type":"print"},{"value":"9783031197727","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19772-7_13","type":"book-chapter","created":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T22:09:58Z","timestamp":1666908598000},"page":"209-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":53,"title":["Global-Local Motion Transformer for\u00a0Unsupervised Skeleton-Based Action Learning"],"prefix":"10.1007","author":[{"given":"Boeun","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyung Jin","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jungho","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin Young","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,28]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Aksan, E., Kaufmann, M., Cao, P., Hilliges, O.: A spatio-temporal transformer for 3D human motion prediction. In: 2021 International Conference on 3D Vision (3DV), pp. 565\u2013574. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00066"},{"key":"13_CR2","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Bai, R., et al.: GCsT: graph convolutional skeleton transformer for action recognition. arXiv preprint arXiv:2109.02860 (2021)","DOI":"10.1109\/ICME52920.2022.9859781"},{"key":"13_CR4","unstructured":"Bao, H., Dong, L., Wei, F.: BEiT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"13_CR5","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)"},{"key":"13_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1007\/978-3-030-58571-6_14","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Cai","year":"2020","unstructured":"Cai, Y., et al.: Learning progressive joint propagation for human motion prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 226\u2013242. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_14"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Pre-trained image processing transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12299\u201312310 (2021)","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, Y.B., Chen, X., Chen, J., Wei, P., Zhang, D., Lin, L.: Hierarchical transformer: Unsupervised representation learning for skeleton-based human action recognition. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2021)","DOI":"10.1109\/ICME51207.2021.9428459"},{"key":"13_CR9","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Cho, S., Maqbool, M., Liu, F., Foroosh, H.: Self-attention network for skeleton-based human action recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 635\u2013644 (2020)","DOI":"10.1109\/WACV45572.2020.9093639"},{"key":"13_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"13_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"13_CR14","unstructured":"Huang, Z., Zeng, Z., Liu, B., Fu, D., Fu, J.: Pixel-BERT: aligning image pixels with text by deep multi-modal transformers. arXiv preprint arXiv:2004.00849 (2020)"},{"key":"13_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Kundu, J.N., Gor, M., Uppala, P.K., Radhakrishnan, V.B.: Unsupervised feature learning of human actions as trajectories in pose embedding manifold. In: 2019 IEEE winter conference on applications of computer vision (WACV), pp. 1459\u20131467. IEEE (2019)","DOI":"10.1109\/WACV.2019.00160"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Li, L., Wang, M., Ni, B., Wang, H., Yang, J., Zhang, W.: 3D human action representation learning via cross-view consistency pursuit. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4741\u20134750 (2021)","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Lin, L., Song, S., Yang, W., Liu, J.: MS2L: multi-task self-supervised learning for skeleton based action recognition. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2490\u20132498 (2020)","DOI":"10.1145\/3394171.3413548"},{"issue":"10","key":"13_CR19","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":"13_CR20","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"13_CR21","unstructured":"Liu, Z., et al.: Video swin transformer. arXiv preprint arXiv:2106.13230 (2021)"},{"key":"13_CR22","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"13_CR23","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems 32 (2019)"},{"key":"13_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108487","volume":"124","author":"V Mazzia","year":"2022","unstructured":"Mazzia, V., Angarano, S., Salvetti, F., Angelini, F., Chiaberge, M.: Action transformer: a self-attention model for short-time pose-based human action recognition. Pattern Recogn. 124, 108487 (2022)","journal-title":"Pattern Recogn."},{"key":"13_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-030-58529-7_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Q Nie","year":"2020","unstructured":"Nie, Q., Liu, Z., Liu, Y.: Unsupervised 3D human pose representation with viewpoint and pose disentanglement. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 102\u2013118. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_7"},{"key":"13_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-030-68796-0_50","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"C Plizzari","year":"2021","unstructured":"Plizzari, C., Cannici, M., Matteucci, M.: Spatial temporal transformer network for skeleton-based action recognition. In: Del Bimbo, A., Cucchiara, R., Sclaroff, S., Farinella, G.M., Mei, T., Bertini, M., Escalante, H.J., Vezzani, R. (eds.) ICPR 2021. LNCS, vol. 12663, pp. 694\u2013701. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68796-0_50"},{"key":"13_CR27","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.ins.2021.04.023","volume":"569","author":"H Rao","year":"2021","unstructured":"Rao, H., Xu, S., Hu, X., Cheng, J., Hu, B.: Augmented skeleton based contrastive action learning with momentum LSTM for unsupervised action recognition. Inf. Sci. 569, 90\u2013109 (2021)","journal-title":"Inf. Sci."},{"key":"13_CR28","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":"13_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-58571-6_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Si","year":"2020","unstructured":"Si, C., Nie, X., Wang, W., Wang, L., Tan, T., Feng, J.: Adversarial self-supervised learning for semi-supervised 3D action recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 35\u201351. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_3"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Su, K., Liu, X., Shlizerman, E.: Predict & cluster: Unsupervised skeleton based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9631\u20139640 (2020)","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Su, Y., Lin, G., Wu, Q.: Self-supervised 3d skeleton action representation learning with motion consistency and continuity. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13328\u201313338 (2021)","DOI":"10.1109\/ICCV48922.2021.01308"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7464\u20137473 (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"13_CR33","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"13_CR34","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":"13_CR35","doi-asserted-by":"crossref","unstructured":"Wang, P., Wen, J., Si, C., Qian, Y., Wang, L.: Contrast-reconstruction representation learning for self-supervised skeleton-based action recognition. arXiv preprint arXiv:2111.11051 (2021)","DOI":"10.1109\/TIP.2022.3207577"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: BEVT: BBERT pretraining of video transformers. arXiv preprint arXiv:2112.01529 (2021)","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"13_CR37","unstructured":"Xu, S., Rao, H., Hu, X., Cheng, J., Hu, B.: Prototypical contrast and reverse prediction: unsupervised skeleton based action recognition. In: IEEE Transactions on Multimedia (2021)"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Yang, S., Liu, J., Lu, S., Er, M.H., Kot, A.C.: Skeleton cloud colorization for unsupervised 3d action representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13423\u201313433 (2021)","DOI":"10.1109\/ICCV48922.2021.01317"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Zheng, C., Zhu, S., Mendieta, M., Yang, T., Chen, C., Ding, Z.: 3D human pose estimation with spatial and temporal transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11656\u201311665 (2021)","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Zheng, N., Wen, J., Liu, R., Long, L., Dai, J., Gong, Z.: Unsupervised representation learning with long-term dynamics for skeleton based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11853"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19772-7_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:51:07Z","timestamp":1710262267000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19772-7_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197710","9783031197727"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19772-7_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"28 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}