{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:26:12Z","timestamp":1767338772820,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031431524"},{"type":"electronic","value":"9783031431531"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43153-1_2","type":"book-chapter","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T21:01:55Z","timestamp":1693861315000},"page":"13-24","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Quasi-Online Detection of\u00a0Take and\u00a0Release Actions from\u00a0Egocentric Videos"],"prefix":"10.1007","author":[{"given":"Rosario","family":"Scavo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Ragusa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni Maria","family":"Farinella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonino","family":"Furnari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,5]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Besari, A.R.A., Saputra, A.A., Chin, W.H., Kubota, N., et al.: Feature-based egocentric grasp pose classification for expanding human-object interactions. In: 2021 IEEE 30th International Symposium on Industrial Electronics (ISIE), pp. 1\u20136. IEEE (2021)","DOI":"10.1109\/ISIE45552.2021.9576369"},{"key":"2_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1007\/978-3-030-01225-0_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Damen","year":"2018","unstructured":"Damen, D., et al.: Scaling egocentric vision: the dataset. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 753\u2013771. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_44"},{"key":"2_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/978-3-319-46454-1_17","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R De Geest","year":"2016","unstructured":"De Geest, R., Gavves, E., Ghodrati, A., Li, Z., Snoek, C., Tuytelaars, T.: Online action detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 269\u2013284. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_17"},{"key":"2_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1007\/978-3-030-30645-8_68","volume-title":"Image Analysis and Processing \u2013 ICIAP 2019","author":"GM Farinella","year":"2019","unstructured":"Farinella, G.M., et al.: VEDI: vision exploitation for data interpretation. In: Ricci, E., Rota Bul\u00f2, S., Snoek, C., Lanz, O., Messelodi, S., Sebe, N. (eds.) ICIAP 2019. LNCS, vol. 11752, pp. 753\u2013763. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30645-8_68"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: RED: reinforced encoder-decoder networks for action anticipation. arXiv preprint arXiv:1707.04818 (2017)","DOI":"10.5244\/C.31.92"},{"key":"2_CR6","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":"2_CR7","doi-asserted-by":"crossref","unstructured":"Gao, M., Zhou, Y., Xu, R., Socher, R., Xiong, C.: WOAD: weakly supervised online action detection in untrimmed videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1915\u20131923 (2021)","DOI":"10.1109\/CVPR46437.2021.00195"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., He, K.: Detecting and recognizing human-object interactions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8359\u20138367 (2018)","DOI":"10.1109\/CVPR.2018.00872"},{"key":"2_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2016.10.018","volume":"155","author":"H Idrees","year":"2017","unstructured":"Idrees, H., et al.: The THUMOS challenge on action recognition for videos \u201cin the wild\u2019\u2019. Comput. Vis. Image Underst. 155, 1\u201323 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Karita, S., et al.: A comparative study on transformer vs RNN in speech applications. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 449\u2013456. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"2_CR11","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":"2_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/978-3-030-01240-3_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Qi","year":"2018","unstructured":"Qi, S., Wang, W., Jia, B., Shen, J., Zhu, S.-C.: Learning human-object interactions by graph parsing neural networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 407\u2013423. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_25"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Ragusa, F., Furnari, A., Farinella, G.M.: MECCANO: a multimodal egocentric dataset for humans behavior understanding in the industrial-like domain. arXiv preprint arXiv:2209.08691 (2022)","DOI":"10.1016\/j.cviu.2023.103764"},{"key":"2_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1007\/978-3-030-01219-9_33","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Shou","year":"2018","unstructured":"Shou, Z., et al.: Online detection of action start in untrimmed, streaming videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 551\u2013568. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_33"},{"key":"2_CR15","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Wang, T., Yang, T., Danelljan, M., Khan, F.S., Zhang, X., Sun, J.: Learning human-object interaction detection using interaction points. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4116\u20134125 (2020)","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"2_CR17","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, pp. 7565\u20137575 (2021)","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"2_CR18","first-page":"1086","volume":"34","author":"M Xu","year":"2021","unstructured":"Xu, M., et al.: Long short-term transformer for online action detection. Adv. Neural. Inf. Process. Syst. 34, 1086\u20131099 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR19","doi-asserted-by":"publisher","unstructured":"Zhao, Y., Kr\u00e4henb\u00fchl, P.: Real-time online video detection with temporal smoothing transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part XXXIV, vol. 13694, pp. 485\u2013502. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19830-4_28","DOI":"10.1007\/978-3-031-19830-4_28"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43153-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T13:24:27Z","timestamp":1730035467000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43153-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031431524","9783031431531"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43153-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Udine","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap2023.org\/","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":"144","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":"85","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":"7","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":"59% - 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","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","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":"https:\/\/iciap2023.org\/satellite-event\/workshops\/","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)"}}]}}