{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:37:32Z","timestamp":1777657052530,"version":"3.51.4"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198298","type":"print"},{"value":"9783031198304","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\/978-3-031-19830-4_37","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T16:21:10Z","timestamp":1666369270000},"page":"653-669","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["A Sliding Window Scheme for\u00a0Online Temporal Action Localization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6863-8551","authenticated-orcid":false,"given":"Young Hwi","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1571-4359","authenticated-orcid":false,"given":"Hyolim","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8512-216X","authenticated-orcid":false,"given":"Seon Joo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"37_CR1","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 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Vijayanarasimhan, S., Seybold, B., Ross, D.A., Deng, J., Sukthankar, R.: Rethinking the faster R-CNN architecture for temporal action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1130\u20131139 (2018)","DOI":"10.1109\/CVPR.2018.00124"},{"issue":"10","key":"37_CR3","doi-asserted-by":"publisher","first-page":"2723","DOI":"10.1109\/TMM.2019.2959977","volume":"22","author":"P Chen","year":"2019","unstructured":"Chen, P., Gan, C., Shen, G., Huang, W., Zeng, R., Tan, M.: Relation attention for temporal action localization. IEEE Trans. Multimedia 22(10), 2723\u20132733 (2019)","journal-title":"IEEE Trans. Multimedia"},{"key":"37_CR4","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":"37_CR5","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 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 809\u2013818 (2020)","DOI":"10.1109\/CVPR42600.2020.00089"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Escorcia, V., Ghanem, B., Niebles, J.C.: Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Chen, K., Sun, C., Nevatia, R.: Turn tap: temporal unit regression network for temporal action proposals. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 3628\u20133636 (2017)","DOI":"10.1109\/ICCV.2017.392"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: RED: reinforced encoder-decoder networks for action anticipation. In: Proceedings of the British Machine Vision Conference (BMVC), pp. 1-11 (2017)","DOI":"10.5244\/C.31.92"},{"key":"37_CR9","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 International Conference on Computer Vision (ICCV), pp. 5542\u20135551 (2019)","DOI":"10.1109\/ICCV.2019.00564"},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"Hosang, J., Benenson, R., Schiele, B.: Learning non-maximum suppression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4507\u20134515 (2017)","DOI":"10.1109\/CVPR.2017.685"},{"key":"37_CR11","unstructured":"Jiang, Y.G., et al.: THUMOS challenge: action recognition with a large number of classes. https:\/\/crcv.ucf.edu\/THUMOS14\/ (2014)"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Kang, H., Kim, K., Ko, Y., Kim, S.J.: CAG-QIL: context-aware actionness grouping via Q imitation learning for online temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 13729\u201313738 (2021)","DOI":"10.1109\/ICCV48922.2021.01347"},{"key":"37_CR13","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":"37_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"Lin, C., et al.: Learning salient boundary feature for anchor-free temporal action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3320\u20133329 (2021)","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"Lin, T., Liu, X., Li, X., Ding, E., Wen, S.: BMN: boundary-matching network for temporal action proposal generation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 3889\u20133898 (2019)","DOI":"10.1109\/ICCV.2019.00399"},{"key":"37_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01225-0_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Lin","year":"2018","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: boundary sensitive network for temporal action proposal generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 3\u201321. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_1"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Q., Wang, Z.: Progressive boundary refinement network for temporal action detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11612\u201311619 (2020)","DOI":"10.1609\/aaai.v34i07.6829"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Liu, X., Hu, Y., Bai, S., Ding, F., Bai, X., Torr, P.H.: Multi-shot temporal event localization: a benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12596\u201312606 (2021)","DOI":"10.1109\/CVPR46437.2021.01241"},{"key":"37_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1007\/978-3-030-01267-0_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Shim","year":"2018","unstructured":"Shim, M., Kim, Y.H., Kim, K., Kim, S.J.: Teaching machines to understand baseball games: large-scale baseball video database for multiple video understanding tasks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 420\u2013437. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_25"},{"key":"37_CR21","doi-asserted-by":"crossref","unstructured":"Shou, Z., Chan, J., Zareian, A., Miyazawa, K., Chang, S.F.: CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5734\u20135743 (2017)","DOI":"10.1109\/CVPR.2017.155"},{"key":"37_CR22","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":"37_CR23","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1049\u20131058 (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"37_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) 30 (2017)"},{"key":"37_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: OadTR: online action detection with transformers. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 7565\u20137575 (2021)","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"37_CR27","unstructured":"Xu, M., Perez Rua, J.M., Zhu, X., Ghanem, B., Martinez, B.: Low-fidelity video encoder optimization for temporal action localization. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) 34 (2021)"},{"key":"37_CR28","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhao, C., Rojas, D.S., Thabet, A., Ghanem, B.: G-TAD: sub-graph localization for temporal action detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10156\u201310165 (2020)","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"37_CR29","doi-asserted-by":"crossref","unstructured":"Xu, M., Gao, M., Chen, Y.T., Davis, L.S., Crandall, D.J.: Temporal recurrent networks for online action detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 5532\u20135541 (2019)","DOI":"10.1109\/ICCV.2019.00563"},{"key":"37_CR30","doi-asserted-by":"crossref","unstructured":"Zeng, R., et al.: Graph convolutional networks for temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 7094\u20137103 (2019)","DOI":"10.1109\/ICCV.2019.00719"},{"key":"37_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, C., Thabet, A.K., Ghanem, B.: Video self-stitching graph network for temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 13658\u201313667 (2021)","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"37_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/978-3-030-58598-3_32","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Zhao","year":"2020","unstructured":"Zhao, P., Xie, L., Ju, C., Zhang, Y., Wang, Y., Tian, Q.: Bottom-up temporal action localization with mutual regularization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 539\u2013555. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_32"},{"key":"37_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2914\u20132923 (2017)","DOI":"10.1109\/ICCV.2017.317"},{"key":"37_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Tang, W., Wang, L., Zheng, N., Hua, G.: Enriching local and global contexts for temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 13516\u201313525 (2021)","DOI":"10.1109\/ICCV48922.2021.01326"}],"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\/978-3-031-19830-4_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T00:03:27Z","timestamp":1666397007000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19830-4_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198298","9783031198304"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19830-4_37","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":"22 October 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)"}}]}}