{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:44:19Z","timestamp":1785822259921,"version":"3.56.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032319357","type":"print"},{"value":"9783032319364","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31936-4_8","type":"book-chapter","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:51:13Z","timestamp":1785819073000},"page":"108-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Continuous Online Action Detection from\u00a0Egocentric Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6344-408X","authenticated-orcid":false,"given":"Riccardo","family":"Santambrogio","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4984-7432","authenticated-orcid":false,"given":"Chiara","family":"Plizzari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1862-4853","authenticated-orcid":false,"given":"Francesca","family":"Palermo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7059-413X","authenticated-orcid":false,"given":"Simone","family":"Mentasti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8306-6739","authenticated-orcid":false,"given":"Matteo","family":"Matteucci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"An, J., Kang, H., Han, S.H., Yang, M.H., Kim, S.J.: MiniRoad: minimal RNN framework for online action detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10341\u201310350 (2023)","DOI":"10.1109\/ICCV51070.2023.00949"},{"key":"8_CR2","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: Proceedings of the International Conference on Machine Learning (ICML), (2021)"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Cai, R., Janaka, N., Kim, H., Chen, Y., Zhao, S., Huang, Y., Hsu, D.: AIGet: transforming everyday moments into hidden knowledge discovery with ai assistance on smart glasses. In: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, pp. 1\u201326 (2025)","DOI":"10.1145\/3706598.3713953"},{"key":"8_CR4","doi-asserted-by":"publisher","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset, pp. 4724\u20134733 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.502","DOI":"10.1109\/CVPR.2017.502"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Carreira, J.A., et al.: Learning from one continuous video stream. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28751\u201328761 (2024)","DOI":"10.1109\/CVPR52733.2024.02716"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., et al.: Learning from one continuous video stream. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28751\u201328761 (2024)","DOI":"10.1109\/CVPR52733.2024.02716"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Chen, J., Mittal, G., Yu, Y., Kong, Y., Chen, M.: GateHuB: gated history unit with background suppression for online action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19925\u201319934 (2022)","DOI":"10.1109\/CVPR52688.2022.01930"},{"key":"8_CR8","doi-asserted-by":"publisher","unstructured":"Cho, K., van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: Encoder\u2013decoder approaches. In: Wu, D., Carpuat, M., Carreras, X., Vecchi, E.M. (eds.) Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, pp. 103\u2013111. Association for Computational Linguistics, Doha, Qatar (2014). https:\/\/doi.org\/10.3115\/v1\/W14-4012, https:\/\/aclanthology.org\/W14-4012\/","DOI":"10.3115\/v1\/W14-4012"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: Rescaling egocentric vision: collection, pipeline and challenges for epic-kitchens-100. Int. J. Comput. Vision, 1\u201323 (2022)","DOI":"10.1007\/s11263-021-01531-2"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"De\u00a0Geest, R., et al.: Online action detection. In: ECCV Workshops (2016)","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"De Geest, R., Tuytelaars, T.: Modeling temporal structure with LSTM for online action detection. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1549\u20131557. IEEE (2018)","DOI":"10.1109\/WACV.2018.00173"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Eun, H., Moon, J., Park, J., Jung, C., Kim, C.: Learning to discriminate information for online action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 809\u2013818 (2020)","DOI":"10.1109\/CVPR42600.2020.00089"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: RED: reinforced encoder-decoder networks for action anticipation (2017). arXiv:1707.04818 arXiv preprint","DOI":"10.5244\/C.31.92"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Gao, M., Xu, M., Davis, L.S., Socher, R., Xiong, C.: StartNet: online detection of action start in untrimmed videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5542\u20135551 (2019)","DOI":"10.1109\/ICCV.2019.00564"},{"key":"8_CR15","unstructured":"Grauman, K., et\u00a0al.: EGO4D: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18995\u201319012 (2022)"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Guermal, M., Ali, A., Dai, R., Bremond, F.: JOADAA: joint online action detection and action anticipation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6889\u20136898 (2024)","DOI":"10.1109\/WACV57701.2024.00674"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Han, T., et al.: Learning from streaming video with orthogonal gradients. In: Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), pp. 13651\u201313660 (2025)","DOI":"10.1109\/CVPR52734.2025.01274"},{"key":"8_CR18","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR19","unstructured":"Jiang, Y.G., et al.: Thumos challenge: action recognition with a large number of classes. In: ECCV Workshop (2014)"},{"key":"8_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107954","volume":"116","author":"YH Kim","year":"2021","unstructured":"Kim, Y.H., Nam, S., Kim, S.J.: Temporally smooth online action detection using cycle-consistent future anticipation. Pattern Recogn. 116, 107954 (2021)","journal-title":"Pattern Recogn."},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Lan, C., Xing, J., Zeng, W., Yuan, C., Liu, J.: Online human action detection using joint classification-regression recurrent neural networks. In: Computer Vision\u2013ECCV 2016, pp. 203\u2013220. Springer (2016)","DOI":"10.1007\/978-3-319-46478-7_13"},{"key":"8_CR22","unstructured":"Lin, K.Q., et al.: Egocentric video-language pretraining (2022). arXiv:2206.01670 arXiv preprint"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Mucha, W., Cuconasu, F., Etori, N.A., Kalokyri, V., Trappolini, G.: Text2Taste: a versatile egocentric vision system for intelligent reading assistance using large language model. In: International Conference on Computers Helping People with Special Needs, pp. 285\u2013291. Springer (2024)","DOI":"10.1007\/978-3-031-62849-8_35"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Shou, Z., et al.: Online detection of action start in untrimmed, streaming videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 534\u2013551 (2018)","DOI":"10.1007\/978-3-030-01219-9_33"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, G., Huang, Y., Wang, L., Lu, T.: Memory-and-anticipation transformer for online action understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13824\u201313835 (2023)","DOI":"10.1109\/ICCV51070.2023.01271"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: OADTR: online action detection with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7565\u20137575 (2021)","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"8_CR27","unstructured":"Xu, M., et al.: Long short-term transformer for online action detection. In: Advances in Neural Information Processing Systems, vol. 34, pp. 1086\u20131099 (2021)"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Kr\u00e4henb\u00fchl, P.: Real-time online video detection with temporal smoothing transformers. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19830-4_28"},{"key":"8_CR29","doi-asserted-by":"publisher","unstructured":"Zhu, S., Voigt, T., Rahimian, F., Ko, J.: On-device training: a first overview on existing systems. ACM Trans. Sen. Netw. 20(6) (2024). https:\/\/doi.org\/10.1145\/3696003","DOI":"10.1145\/3696003"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31936-4_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:51:20Z","timestamp":1785819080000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31936-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"ISBN":["9783032319357","9783032319364"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31936-4_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"assertion":[{"value":"5 August 2026","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":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}