{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:58:11Z","timestamp":1742943491662,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781094"},{"type":"electronic","value":"9783031781100"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-78110-0_13","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T21:53:03Z","timestamp":1733089983000},"page":"196-211","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Temporal Action Segmentation and\u00a0Detection with\u00a0Hierarchical Task Grammar"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6604-7299","authenticated-orcid":false,"given":"Qiu","family":"Yihui","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7788-8368","authenticated-orcid":false,"given":"Deepu","family":"Rajan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"13_CR1","unstructured":"Song, Y., Byrne, E., Nagarajan, T., Wang, H., Martin, M., Torresani, L.: Ego4d task-step: toward hierarchical understanding of procedural activities. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"13_CR2","unstructured":"Gong, D., Lee, J., Jung, D., Kwak, S., Cho, M.: Activity grammars for temporal action segmentation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"issue":"8","key":"13_CR3","doi-asserted-by":"publisher","first-page":"2538","DOI":"10.1109\/TPAMI.2020.2976971","volume":"43","author":"S Qi","year":"2020","unstructured":"Qi, S., Jia, B., Huang, S., Wei, P., Zhu, S.C.: A generalized earley parser for human activity parsing and prediction. IEEE Trans. Pattern Anal. Mach. Intell. 43(8), 2538\u20132554 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Qi, S., Huang, S., Wei, P., Zhu, S.C.: Predicting human activities using stochastic grammar. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1164\u20131172 (2017)","DOI":"10.1109\/ICCV.2017.132"},{"issue":"4","key":"13_CR5","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1016\/S0019-9958(59)80017-6","volume":"2","author":"N Chomsky","year":"1959","unstructured":"Chomsky, N.: A note on phrase structure grammars. Inf. Control 2(4), 393\u2013395 (1959)","journal-title":"Inf. Control"},{"issue":"8","key":"13_CR6","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1145\/359576.359579","volume":"21","author":"J Backus","year":"1978","unstructured":"Backus, J.: Can programming be liberated from the von Neumann style? a functional style and its algebra of programs. Commun. ACM 21(8), 613\u2013641 (1978)","journal-title":"Commun. ACM"},{"key":"13_CR7","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 CVPR, pp. 754\u2013763 (2017)","DOI":"10.1109\/CVPR.2017.140"},{"key":"13_CR8","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s10462-023-10650-w","volume":"57","author":"K Hu","year":"2024","unstructured":"Hu, K., Shen, C., Wang, T., et al.: Overview of temporal action detection based on deep learning. Artif. Intell. Rev. 57, 26 (2024)","journal-title":"Artif. Intell. Rev."},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Y., Sugano, Y., Sato, Y.: Improving action segmentation via graph-based temporal reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14024\u201314034 (2020)","DOI":"10.1109\/CVPR42600.2020.01404"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Ahn, H., Lee, D.: Refining action segmentation with hierarchical video representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16302\u201316310 (2021)","DOI":"10.1109\/ICCV48922.2021.01599"},{"key":"13_CR11","unstructured":"Xu, Z., Rawat, Y., Wong, Y., Kankanhalli, M.S., Shah, M.: Don\u2019t pour cereal into coffee: differentiable temporal logic for temporal action segmentation. In: Advances Neural on Information Processing Systems, vol. 35, pp. 14890\u201314903 (2022)"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Lei, P., Todorovic, S.: Temporal deformable residual networks for action segmentation in videos. In: CVPR, pp. 6742\u20136751 (2018)","DOI":"10.1109\/CVPR.2018.00705"},{"issue":"6","key":"13_CR13","doi-asserted-by":"publisher","first-page":"6647","DOI":"10.1109\/TPAMI.2020.3021756","volume":"45","author":"S Li","year":"2020","unstructured":"Li, S., Farha, Y.A., 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)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Gall, J.: MS-TCN: multi-stage temporal convolutional network for action segmentation. In: CVPR, pp. 3575\u20133584 (2019)","DOI":"10.1109\/CVPR.2019.00369"},{"key":"13_CR15","unstructured":"Yi, F., Wen, H., Jiang, T.: ASFormer: transformer for action segmentation. In BMVC (2021)"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, C.L., Wu, J., Li, Y.: Actionformer: localizing moments of actions with transformers. In: ECCV 2022, pp. 492\u2013510. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Fan, Z.: Temporal action localization with two-stream segment-based RNN. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3400\u20133404. IEEE (2017)","DOI":"10.1109\/ICIP.2017.8296913"},{"key":"13_CR18","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 CVPR 2017, pp. 754\u2013763 (2017)","DOI":"10.1109\/CVPR.2017.140"},{"issue":"4","key":"13_CR19","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\u201379 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Vo, N.N., Bobick, A.F.: From stochastic grammar to bayes network: probabilistic parsing of complex activity. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2641\u20132648 (2014 )","DOI":"10.1109\/CVPR.2014.338"},{"key":"13_CR21","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 CVPR, pp. 5987\u20135996 (2018)","DOI":"10.1109\/CVPR.2018.00627"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Qi, S., Huang, S., Wei, P., Zhu, S.-C.: Predicting human activities using stochastic grammar. In: Proceedings of IEEE International Conference on Computer Vision, pp. 1173\u20131181 (2017)","DOI":"10.1109\/ICCV.2017.132"},{"key":"13_CR23","unstructured":"Qi, S., Jia, B., Zhu, S.-C.: Generalized earley parser: bridging symbolic grammars and sequence data for future prediction. In: Proceedings of IEEE International Conference on Machine Learning, pp. 4168\u20134176 (2018)"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Pei, M., Jia, Y., Zhu, S.C.: Parsing video events with goal inference and intent prediction. In: ICCV, pp. 487\u2013494. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126279"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Si, Z., Pei, M., Yao, B., Zhu, S.-C.: Unsupervised learning of event and-or grammar and semantics from video. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126223"},{"key":"13_CR26","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":"13_CR27","doi-asserted-by":"crossref","unstructured":"Tang, Y., Zhang, X., Ma, L., Wang, J., Chen, S., Jiang, Y.G.: Non-local netvlad encoding for video classification. In: Proceedings of ECCV (2018)","DOI":"10.1007\/978-3-030-11018-5_20"},{"key":"13_CR28","unstructured":"Ding, L., Xu, C.: Weakly-supervised action segmentation with iterative soft boundary assignment. In: Proceedings of the IEEE CVPR (2018)"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Lei, P., Todorovic, S.: Temporal deformable residual networks for action segmentation in videos. In: Proceedings of the IEEE CVPR (2018)","DOI":"10.1109\/CVPR.2018.00705"},{"issue":"10","key":"13_CR30","doi-asserted-by":"publisher","first-page":"11484","DOI":"10.1109\/TPAMI.2023.3284080","volume":"45","author":"D Singhania","year":"2023","unstructured":"Singhania, D., Rahaman, R., Yao, A.: C2F-TCN: a framework for semi-and fully-supervised temporal action segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(10), 11484\u201311501 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Wang, H., Singh, M.K., Torresani, L.: Ego-only: egocentric action detection without exocentric transferring. In Proceedings of the IEEE CVPR (2023)","DOI":"10.1109\/ICCV51070.2023.00484"},{"key":"13_CR32","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 CVPR (2014)","DOI":"10.1109\/CVPR.2014.105"},{"key":"13_CR33","unstructured":"Gramman, K., et al.: Ego4d: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE CVPR (2022)"},{"key":"13_CR34","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. (2023)","DOI":"10.1109\/TPAMI.2023.3327284"},{"key":"13_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, pp. 729\u2013738 (2013)","DOI":"10.1145\/2493432.2493482"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: Rescaling egocentric vision: collection, pipeline and challenges for epic-kitchens-100. Int. J. Comput. Vis. 1\u201323 (2022)","DOI":"10.1007\/s11263-021-01531-2"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78110-0_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:32:41Z","timestamp":1733095961000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78110-0_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031781094","9783031781100"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78110-0_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 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"}}]}}