{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:30:34Z","timestamp":1777570234022,"version":"3.51.4"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031781247","type":"print"},{"value":"9783031781254","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78125-4_26","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T06:09:52Z","timestamp":1733292592000},"page":"380-395","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["2by2: Weakly-Supervised Learning for\u00a0Global Action Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7566-9771","authenticated-orcid":false,"given":"Elena","family":"Bueno-Benito","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2669-400X","authenticated-orcid":false,"given":"Mariella","family":"Dimiccoli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Aakur, S.N., Sarkar, S.: A perceptual prediction framework for self supervised event segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00129"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., Bojanowski, P., Agrawal, N., Sivic, J., Laptev, I., Lacoste-Julien, S.: Unsupervised learning from narrated instruction videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4575\u20134583 (2016)","DOI":"10.1109\/CVPR.2016.495"},{"key":"26_CR3","unstructured":"Andrew, G., Arora, R., Bilmes, J., Livescu, K.: Deep canonical correlation analysis. In: Deep Canonical Correlation Analysis (ICML), pp. 1247\u20131255 (2013)"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Bahrami, E., Francesca, G., Gall, J.: How much temporal long-term context is needed for action segmentation? In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00950"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Behrmann, N., Golestaneh, S.A., Kolter, Z., Gall, J., Noroozi, M.: Unified fully and timestamp supervised temporal action segmentation via sequence to sequence translation. In: Proceedings of the European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19833-5_4"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Bueno-Benito, E., Tura, B., Dimiccoli, M.: Leveraging triplet loss for unsupervised action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2023)","DOI":"10.52591\/lxai202306185"},{"key":"26_CR8","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"26_CR9","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 (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00829"},{"key":"26_CR10","unstructured":"Cuturi, M., Blondel, M.: Soft-DTW: a differentiable loss function for time-series. In: International Conference on Machine Learning (ICML) (2017)"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Dias, C., Dimiccoli, M.: Learning event representations by encoding the temporal context. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops. vol. 11131, pp. 587\u2013596 (2018)","DOI":"10.1007\/978-3-030-11015-4_44"},{"key":"26_CR12","doi-asserted-by":"publisher","first-page":"1476","DOI":"10.1109\/TIP.2020.3044448","volume":"30","author":"M Dimiccoli","year":"2020","unstructured":"Dimiccoli, M., Wendt, H.: Learning event representations for temporal segmentation of image sequences by dynamic graph embedding. IEEE Trans. Image Process. 30, 1476\u20131486 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Ding, G., Sener, F., Yao, A.: Temporal action segmentation: an analysis of modern techniques. IEEE Trans. Pattern Anal. Mach. Intell. 46(2), 1011\u20131030 (2023)","DOI":"10.1109\/TPAMI.2023.3327284"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Ding, G., Yao, A.: Temporal action segmentation with high-level complex activity labels. IEEE Trans. Multimedia 25, 1928\u20131939 (2023)","DOI":"10.1109\/TMM.2022.3231099"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Donahue, G., Elhamifar, E.: Learning to predict activity progress by self-supervised video alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01766"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Du, Z., Wang, X., Zhou, G., Wang, Q.: Fast and unsupervised action boundary detection for action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00332"},{"key":"26_CR17","unstructured":"Dvornik, N., Hadji, I., Derpanis, K.G., Garg, A., Jepson, A.D.: Drop-DTW: aligning common signal between sequences while dropping outliers. In: Advances in Neural Information Processing Systems (2021)"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Aytar, Y., Tompson, J., Sermanet, P., Zisserman, A.: Temporal cycle-consistency learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00190"},{"key":"26_CR19","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 (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00369"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Haresh, S., et al.: Learning by aligning videos in time. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00550"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"He, Y., Yuan, Z., Wu, Y., Cheng, L., Deng, D., Wu, Y.: ViSTec: video modeling for sports technique recognition and tactical analysis. In: Proceedings of the Conference on Artificial Intelligence (AAAI) (2024)","DOI":"10.1609\/aaai.v38i8.28692"},{"key":"26_CR22","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.105"},{"key":"26_CR23","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 (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01234"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Kumar, S., Haresh, S., Ahmed, A., Konin, A., Zia, M.Z., Tran, Q.H.: Unsupervised action segmentation by joint representation learning and online clustering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01954"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Li, J., Todorovic, S.: Action shuffle alternating learning for unsupervised action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01244"},{"key":"26_CR27","doi-asserted-by":"crossref","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. 45(6), 6647\u20136658 (2020)","DOI":"10.1109\/TPAMI.2020.3021756"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Xue, Z., Xu, H.: OTAS: unsupervised boundary detection for object-centric temporal action segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2024)","DOI":"10.1109\/WACV57701.2024.00631"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Liu, W., Tekin, B., Coskun, H., Vineet, V., Fua, P., Pollefeys, M.: Learning to align sequential actions in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00222"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Lu, Z., Elhamifar, E.: Weakly-supervised action segmentation and alignment via transcript-aware union-of-subspaces learning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00798"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Lu, Z., Elhamifar, E.: Set-supervised action learning in procedural task videos via pairwise order consistency. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19871\u201319881 (2022)","DOI":"10.1109\/CVPR52688.2022.01928"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Lu, Z., Elhamifar, E.: FACT: frame-action cross-attention temporal modeling for efficient action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01721"},{"key":"26_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103298","volume":"213","author":"YB Ng","year":"2021","unstructured":"Ng, Y.B., Fernando, B.: Weakly supervised action segmentation with effective use of attention and self-attention. Comput. Vis. Image Underst. 213, 103298 (2021)","journal-title":"Comput. Vis. Image Underst."},{"key":"26_CR34","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/s11263-015-0851-8","volume":"119","author":"M Rohrbach","year":"2016","unstructured":"Rohrbach, M., et al.: Recognizing fine-grained and composite activities using hand-centric features and script data. Int. J. Comput. Vis. (IJCV) 119, 346\u2013373 (2016)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Sarfraz, M.S., Murray, N., Sharma, V., Diba, A., Gool, L.V., Stiefelhagen, R.: Temporally-weighted hierarchical clustering for unsupervised action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01107"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Sarfraz, M.S., Sharma, V., Stiefelhagen, R.: Efficient parameter-free clustering using first neighbor relations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00914"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Sener, F., Yao, A.: Unsupervised learning and segmentation of complex activities from video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00873"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Sermanet, P., et al.: Time-contrastive networks: self-supervised learning from video. In: IEEE International Conference on Robotics and Automation (ICRA) (2018)","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"26_CR39","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Sirnam\u00a0Swetha, Hilde\u00a0Kuehne, Y.S.R., Shah, M.: Unsupervised discriminative embedding for sub-action learning in complex activities. In: IEEE International Conference on Image Processing (ICIP) (2021)","DOI":"10.1109\/ICIP42928.2021.9506759"},{"key":"26_CR41","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. 44(10), 6196\u20136208 (2022)","DOI":"10.1109\/TPAMI.2021.3089127"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Tran, Q.H., Mehmood, A., Ahmed, M., Naufil, M., Konin, A., Zia, M.Z.: Permutation-aware activity segmentation via unsupervised frame-to-segment alignment. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2024)","DOI":"10.1109\/WACV57701.2024.00630"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"VidalMata, R.G., Scheirer, W.J., Kukleva, A., Cox, D.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 (WACV) (2021)","DOI":"10.1109\/WACV48630.2021.00128"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: SSCAP: self-supervised co-occurrence action parsing for unsupervised temporal action segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2022)","DOI":"10.1109\/WACV51458.2022.00025"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Xu, A., Zheng, W.S.: Efficient and effective weakly-supervised action segmentation via action-transition-aware boundary alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01728"},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Xu, M., Gould, S.: Temporally consistent unbalanced optimal transport for unsupervised action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01385"},{"key":"26_CR48","unstructured":"Yi, F., Wen, H., Jiang, T.: ASFormer: transformer for action segmentation. In: The British Machine Vision Conference (BMVC) (2021)"},{"key":"26_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, R., Wang, S., Duan, Y., Tang, Y., Zhang, Y., Tan, Y.P.: HOI-aware adaptive network for weakly-supervised action segmentation. In: Proceedings of the Conference on Artificial Intelligence (AAAI) (2023)","DOI":"10.24963\/ijcai.2023\/191"},{"key":"26_CR50","doi-asserted-by":"crossref","unstructured":"Zuckerman, I., et al.: Depth over RGB: automatic evaluation of open surgery skills using depth camera. Int. J. Comput. Assist. Radiol. Surg. 19(25), 1\u20139 (2024)","DOI":"10.1007\/s11548-024-03158-3"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78125-4_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T07:08:38Z","timestamp":1733296118000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78125-4_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031781247","9783031781254"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78125-4_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}