{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T15:58:52Z","timestamp":1778687932999,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198328","type":"print"},{"value":"9783031198335","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\/978-3-031-19833-5_4","type":"book-chapter","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:40:30Z","timestamp":1667522430000},"page":"52-68","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":78,"title":["Unified Fully and\u00a0Timestamp Supervised Temporal Action Segmentation via\u00a0Sequence to\u00a0Sequence Translation"],"prefix":"10.1007","author":[{"given":"Nadine","family":"Behrmann","sequence":"first","affiliation":[]},{"given":"S. Alireza","family":"Golestaneh","sequence":"additional","affiliation":[]},{"given":"Zico","family":"Kolter","sequence":"additional","affiliation":[]},{"given":"J\u00fcrgen","family":"Gall","sequence":"additional","affiliation":[]},{"given":"Mehdi","family":"Noroozi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Abu Farha, Y., Gall, J.: MS-TCN: multi-stage temporal convolutional network for action segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00369"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: ViViT: a video vision transformer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"4_CR3","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)"},{"key":"4_CR4","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML (2021)"},{"key":"4_CR5","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":"4_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? CVPR, a new model and the kinetics dataset (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"4_CR7","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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00947"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-xl: attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860 (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"4_CR9","unstructured":"Ding, L., Xu, C.: Weakly-supervised action segmentation with iterative soft boundary assignment. In: CVPR (2018)"},{"key":"4_CR10","unstructured":"Ding, L., Xu, C.: Weakly-supervised action segmentation with iterative soft boundary assignment. In: CVPR (2018)"},{"key":"4_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Fathi, A., Ren, X., Rehg, J.M.: Learning to recognize objects in egocentric activities. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Gammulle, H., Denman, S., Sridharan, S., Fookes, C.: Fine-grained action segmentation using the semi-supervised action GAN. Pattern Recogn. 98, 107039 (2020)","DOI":"10.1016\/j.patcog.2019.107039"},{"key":"4_CR14","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: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01653"},{"key":"4_CR15","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":"4_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Y., Sugano, Y., Sato, Y.: Improving action segmentation via graph-based temporal reasoning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01404"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Ishikawa, Y., Kasai, S., Aoki, Y., Kataoka, H.: Alleviating over-segmentation errors by detecting action boundaries. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00237"},{"key":"4_CR18","unstructured":"Karaman, S., Seidenari, L., Bimbo, A.D.: Fast saliency based pooling of fisher encoded dense trajectories. In: ECCV Workshops (2014)"},{"key":"4_CR19","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: CVPR (2014)","DOI":"10.1109\/CVPR.2014.105"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Gall, J., Serre, T.: An end-to-end generative framework for video segmentation and recognition. In: WACV (2016)","DOI":"10.1109\/WACV.2016.7477701"},{"issue":"4","key":"4_CR21","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1109\/TPAMI.2018.2884469","volume":"42","author":"H Kuehne","year":"2020","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 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR22","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Lei, P., Todorovic, S.: Temporal deformable residual networks for action segmentation in videos. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00705"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Li, J., Lei, P., Todorovic, S.: Weakly supervised energy-based learning for action segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00634"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Li, S.J., Abu Farha, Y., Liu, Y., Cheng, M.M., Gall, J.: MS-TCN++: multi-stage temporal convolutional network for action segmentation. In: TPAMI (2020)","DOI":"10.1109\/TPAMI.2020.3021756"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Li, Z., Abu Farha, Y., Gall, J.: Temporal action segmentation from timestamp supervision. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00826"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Nawrot, P., et al.: Hierarchical transformers are more efficient language models. arXiv preprint arXiv:2110.13711 (2021)","DOI":"10.18653\/v1\/2022.findings-naacl.117"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Richard, A., Gall, J.: Temporal action detection using a statistical language model. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.341"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Richard, A., Kuehne, H., Gall, J.: Action sets: weakly supervised action segmentation without ordering constraints. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00627"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Richard, A., Kuehne, H., Iqbal, A., Gall, J.: NeuralNetwork-Viterbi: a framework for weakly supervised video learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00771"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Amin, S., Andriluka, M., Schiele, B.: A database for fine grained activity detection of cooking activities. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"4_CR32","unstructured":"Singhania, D., Rahaman, R., Yao, A.: Coarse to fine multi-resolution temporal convolutional network. arXiv preprint arXiv:2105.10859 (2021)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Souri, Y., Abu Farha, Y., Despinoy, F., Francesca, G., Gall, J.: FIFA: fast inference approximation for action segmentation. In: GCPR (2021)","DOI":"10.1007\/978-3-030-92659-5_18"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Souri, Y., Fayyaz, M., Minciullo, L., Francesca, G., Gall, J.: Fast weakly supervised action segmentation using mutual consistency. In: TPAMI (2021)","DOI":"10.1109\/TPAMI.2021.3089127"},{"key":"4_CR35","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 (2013)","DOI":"10.1145\/2493432.2493482"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Tang, K., Fei-Fei, L., Koller, D.: Learning latent temporal structure for complex event detection. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247808"},{"key":"4_CR37","unstructured":"Tay, Y., et al.: Long range arena : a benchmark for efficient transformers. In: ICLR (2021)"},{"key":"4_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"4_CR39","unstructured":"Wang, D., Hu, D., Li, X., Dou, D.: Temporal relational modeling with self-supervision for action segmentation. arXiv preprint arXiv:2012.07508 (2020)"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhu, Y., Adam, H., Yuille, A., Chen, L.C.: MaX-DeepLab: end-to-end panoptic segmentation with mask transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"4_CR41","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":"4_CR42","unstructured":"Yi, F., Wen, H., Jiang, T.: ASFormer: Transformer for action segmentation. In: BMVC (2021)"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"4_CR44","unstructured":"Zhu, C., et al.: Long-short transformer: efficient transformers for language and vision. In: NeurIPS (2021)"}],"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\/978-3-031-19833-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T15:28:19Z","timestamp":1673278099000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19833-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198328","9783031198335"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19833-5_4","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":"4 November 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)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}