{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T17:05:39Z","timestamp":1761239139955,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985364"},{"type":"electronic","value":"9789819985371"}],"license":[{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"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\/978-981-99-8537-1_16","type":"book-chapter","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:02:17Z","timestamp":1703530937000},"page":"195-206","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Prototypical Transformer for\u00a0Weakly Supervised Action Segmentation"],"prefix":"10.1007","author":[{"given":"Tao","family":"Lin","sequence":"first","affiliation":[]},{"given":"Xiaobin","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Weishi","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,26]]},"reference":[{"key":"16_CR1","unstructured":"Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: KDD Workshop, Seattle, WA, USA, vol.\u00a010, pp. 359\u2013370. (1994)"},{"key":"16_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1007\/978-3-319-10602-1_41","volume-title":"Computer Vision \u2013 ECCV 2014","author":"P Bojanowski","year":"2014","unstructured":"Bojanowski, P., et al.: Weakly supervised action labeling in videos under ordering constraints. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 628\u2013643. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_41"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Chang, C.Y., Huang, D.A., Sui, Y., Fei-Fei, L., Niebles, J.C.: D3TW: discriminative differentiable dynamic time warping for weakly supervised action alignment and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3546\u20133555. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00366"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Chang, X., Tung, F., Mori, G.: Learning discriminative prototypes with dynamic time warping. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8395\u20138404. IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.00829"},{"key":"16_CR5","unstructured":"Ding, L., Xu, C.: Weakly-supervised action segmentation with iterative soft boundary assignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6508\u20136516 (2018)"},{"key":"16_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"},{"key":"16_CR7","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256. JMLR Workshop and Conference Proceedings (2010)"},{"key":"16_CR8","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1007\/978-3-031-18913-5_32","volume-title":"Pattern Recognition and Computer Vision","author":"J Guo","year":"2022","unstructured":"Guo, J., Xue, W., Guo, L., Yuan, T., Chen, S.: Multi-level temporal relation graph for continuous sign language recognition. In: Yu, S., et al. (eds.) PRCV 2022, Part III. LNCS, vol. 13536, pp. 408\u2013419. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-18913-5_32"},{"key":"16_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/978-3-319-46493-0_9","volume-title":"Computer Vision \u2013 ECCV 2016","author":"D-A Huang","year":"2016","unstructured":"Huang, D.-A., Fei-Fei, L., Niebles, J.C.: Connectionist temporal modeling for weakly supervised action labeling. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 137\u2013153. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_9"},{"key":"16_CR10","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1007\/978-3-031-18913-5_21","volume-title":"Pattern Recognition and Computer Vision","author":"P Ji","year":"2022","unstructured":"Ji, P., Yang, B., Zhang, T., Zou, Y.: Consensus-guided keyword targeting for video captioning. In: Yu, S., et al. (eds.) PRCV 2022, Part III. LNCS, vol. 13536, pp. 270\u2013281. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-18913-5_21"},{"key":"16_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Koller, O., Zargaran, S., Ney, H.: Re-sign: re-aligned end-to-end sequence modelling with deep recurrent CNN-HMMS. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4297\u20134305. IEEE (2017)","DOI":"10.1109\/CVPR.2017.364"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Arslan, A.B., Serre, T.: The language of actions: recovering the syntax and semantics of goal-directed human activities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 780\u2013787. IEEE (2014)","DOI":"10.1109\/CVPR.2014.105"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Gall, J., Serre, T.: An end-to-end generative framework for video segmentation and recognition. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp.\u00a01\u20138. IEEE (2016)","DOI":"10.1109\/WACV.2016.7477701"},{"key":"16_CR15","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.cviu.2017.06.004","volume":"163","author":"H Kuehne","year":"2017","unstructured":"Kuehne, H., Richard, A., Gall, J.: Weakly supervised learning of actions from transcripts. Comput. Vis. Image Underst. 163, 78\u201389 (2017)","journal-title":"Comput. Vis. Image Underst."},{"issue":"4","key":"16_CR16","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1109\/TPAMI.2018.2884469","volume":"42","author":"H Kuehne","year":"2018","unstructured":"Kuehne, H., Richard, A., Gall, J.: A hybrid RNN-HMM approach for weakly supervised temporal action segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 42(4), 765\u2013779 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR17","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 156\u2013165 (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Li, J., Lei, P., Todorovic, S.: Weakly supervised energy-based learning for action segmentation. In: IEEE\/CVF International Conference on Computer Vision, pp. 6242\u20136250. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00634"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Richard, A., Kuehne, H., Gall, J.: Weakly supervised action learning with RNN based fine-to-coarse modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 754\u2013763. IEEE (2017)","DOI":"10.1109\/CVPR.2017.140"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Richard, A., Kuehne, H., Iqbal, A., Gall, J.: NeuralNetwork-Viterbi: a framework for weakly supervised video learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7386\u20137395. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00771"},{"key":"16_CR21","unstructured":"Ridley, J., Coskun, H., Tan, D.J., Navab, N., Tombari, F.: Transformers in action: weakly supervised action segmentation. arXiv preprint arXiv:2201.05675 (2022)"},{"issue":"10","key":"16_CR22","doi-asserted-by":"publisher","first-page":"6196","DOI":"10.1109\/TPAMI.2021.3089127","volume":"44","author":"Y Souri","year":"2021","unstructured":"Souri, Y., Fayyaz, M., Minciullo, L., Francesca, G., Gall, J.: Fast weakly supervised action segmentation using mutual consistency. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 6196\u20136208 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"16_CR24","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1007\/978-3-031-18907-4_29","volume-title":"Pattern Recognition and Computer Vision","author":"B Yang","year":"2022","unstructured":"Yang, B., Zhang, T., Zou, Y.: Clip meets video captioning: Concept-aware representation learning does matter. In: Yu, S., et al. (eds.) PRCV 2022, Part I. LNCS, vol. 13534, pp. 368\u2013381. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-18907-4_29"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2914\u20132923 (2017)","DOI":"10.1109\/ICCV.2017.317"}],"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\/978-981-99-8537-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:09:25Z","timestamp":1703531365000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8537-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,26]]},"ISBN":["9789819985364","9789819985371"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8537-1_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,26]]},"assertion":[{"value":"26 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)"}}]}}