{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:18:24Z","timestamp":1783527504868,"version":"3.55.0"},"publisher-location":"Cham","reference-count":39,"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_17","type":"book-chapter","created":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T22:09:58Z","timestamp":1666908598000},"page":"279-296","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["A Generalized and Robust Framework for\u00a0Timestamp Supervision in\u00a0Temporal Action Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4260-027X","authenticated-orcid":false,"given":"Rahul","family":"Rahaman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0555-1405","authenticated-orcid":false,"given":"Dipika","family":"Singhania","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9542-509X","authenticated-orcid":false,"given":"Alexandre","family":"Thiery","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7418-6141","authenticated-orcid":false,"given":"Angela","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,28]]},"reference":[{"key":"17_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1007\/978-3-030-01219-9_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Alwassel","year":"2018","unstructured":"Alwassel, H., Caba Heilbron, F., Escorcia, V., Ghanem, B.: Diagnosing error in temporal action detectors. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 264\u2013280. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_16"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"17_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 (2019)","DOI":"10.1109\/CVPR.2019.00366"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Chen, M.H., Li, B., Bao, Y., AlRegib, G., Kira, Z.: Action segmentation with joint self-supervised temporal domain adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9454\u20139463 (2020)","DOI":"10.1109\/CVPR42600.2020.00947"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc. Ser. B (Methodol.) 39(1), 1\u201338 (1977). https:\/\/www.jstor.org\/stable\/2984875\u2019","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"17_CR6","unstructured":"Ding, G., Yao, A.: Temporal action segmentation with high-level complex activity labels. arXiv preprint arXiv:2108.06706 (2021)"},{"key":"17_CR7","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":"17_CR8","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":"17_CR9","doi-asserted-by":"crossref","unstructured":"Fathi, A., Ren, X., Rehg, J.M.: Learning to recognize objects in egocentric activities. In: CVPR 2011, pp. 3281\u20133288. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Fayyaz, M., Gall, J.: SCT: set constrained temporal transformer for set supervised action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020","DOI":"10.1109\/CVPR42600.2020.00058"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Gao, S.H., Han, Q., Li, Z.Y., Peng, P., Wang, L., Cheng, M.M.: Global2local: Efficient structure search for video action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16805\u201316814 (2021)","DOI":"10.1109\/CVPR46437.2021.01653"},{"key":"17_CR12","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":"17_CR13","doi-asserted-by":"crossref","unstructured":"Ju, C., Zhao, P., Chen, S., Zhang, Y., Wang, Y., Tian, Q.: Divide and conquer for single-frame temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13455\u201313464 (2021)","DOI":"10.1109\/ICCV48922.2021.01320"},{"key":"17_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980 (2014)"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Arslan, A., Serre, T.: The language of actions: recovering the syntax and semantics of goal-directed human activities. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 780\u2013787 (2014)","DOI":"10.1109\/CVPR.2014.105"},{"issue":"4","key":"17_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":"17_CR17","doi-asserted-by":"crossref","unstructured":"Kukleva, A., Kuehne, H., Sener, F., Gall, J.: Unsupervised learning of action classes with continuous temporal embedding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12066\u201312074 (2019)","DOI":"10.1109\/CVPR.2019.01234"},{"key":"17_CR18","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":"17_CR19","doi-asserted-by":"crossref","unstructured":"Li, J., Lei, P., Todorovic, S.: Weakly supervised energy-based learning for action segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6243\u20136251 (2019)","DOI":"10.1109\/ICCV.2019.00634"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Li, J., Todorovic, S.: Set-constrained viterbi for set-supervised action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020","DOI":"10.1109\/CVPR42600.2020.01083"},{"key":"17_CR21","unstructured":"Li, S.J., AbuFarha, Y., Liu, Y., Cheng, M.M., Gall, J.: MS-TCN++: multi-stage temporal convolutional network for action segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (2020)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Li, Z., Abu Farha, Y., Gall, J.: Temporal action segmentation from timestamp supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8365\u20138374 (2021)","DOI":"10.1109\/CVPR46437.2021.00826"},{"key":"17_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1007\/978-3-030-58548-8_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"F Ma","year":"2020","unstructured":"Ma, F., et al.: SF-Net: single-frame supervision for temporal action localization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 420\u2013437. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_25"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Moltisanti, D., Fidler, S., Damen, D.: Action recognition from single timestamp supervision in untrimmed videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9915\u20139924 (2019)","DOI":"10.1109\/CVPR.2019.01015"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Moltisanti, D., Wray, M., Mayol-Cuevas, W., Damen, D.: Trespassing the boundaries: labeling temporal bounds for object interactions in egocentric video. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2886\u20132894 (2017)","DOI":"10.1109\/ICCV.2017.314"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Rashid, M., Kjellstrom, H., Lee, Y.J.: Action graphs: weakly-supervised action localization with graph convolution networks. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), March 2020","DOI":"10.1109\/WACV45572.2020.9093404"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Richard, A., Gall, J.: Temporal action detection using a statistical language model. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3131\u20133140 (2016)","DOI":"10.1109\/CVPR.2016.341"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Richard, A., Kuehne, H., Gall, J.: Action sets: weakly supervised action segmentation without ordering constraints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5987\u20135996 (2018)","DOI":"10.1109\/CVPR.2018.00627"},{"key":"17_CR29","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 Conference on Computer Vision and Pattern Recognition, pp. 7386\u20137395 (2018)","DOI":"10.1109\/CVPR.2018.00771"},{"key":"17_CR30","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"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Sener, F., Yao, A.: Unsupervised learning and segmentation of complex activities from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8368\u20138376 (2018)","DOI":"10.1109\/CVPR.2018.00873"},{"key":"17_CR32","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Singh, B., Marks, T.K., Jones, M., Tuzel, O., Shao, M.: A multi-stream bi-directional recurrent neural network for fine-grained action detection, pp. 1961\u20131970 (2016)","DOI":"10.1109\/CVPR.2016.216"},{"key":"17_CR34","unstructured":"Singhania, D., Rahaman, R., Yao, A.: Coarse to fine multi-resolution temporal convolutional network. arXiv preprint arXiv:2105.10859 (2021)"},{"key":"17_CR35","doi-asserted-by":"crossref","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. (2021)","DOI":"10.1109\/TPAMI.2021.3089127"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Stein, S., McKenna, S.J.: Combining embedded accelerometers with computer vision for recognizing food preparation activities. In: Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pp. 729\u2013738. ACM (2013)","DOI":"10.1145\/2493432.2493482"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"VidalMata, R.G., Scheirer, W.J., Kukleva, A., Cox, D., Kuehne, H.: Joint visual-temporal embedding for unsupervised learning of actions in untrimmed sequences. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1238\u20131247 (2021)","DOI":"10.1109\/WACV48630.2021.00128"},{"key":"17_CR38","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":"17_CR39","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"}],"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_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:50:48Z","timestamp":1710262248000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19772-7_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197710","9783031197727"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19772-7_17","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)"}}]}}