{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:25:57Z","timestamp":1778257557456,"version":"3.51.4"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200793","type":"print"},{"value":"9783031200809","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\/978-3-031-20080-9_7","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T19:59:12Z","timestamp":1667419152000},"page":"105-121","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":76,"title":["ReAct: Temporal Action Detection with\u00a0Relational Queries"],"prefix":"10.1007","author":[{"given":"Dingfeng","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-nms-improving object detection with one line of code. In: Proceedings of the IEEE International Conference on Computer vision, pp. 5561\u20135569 (2017)","DOI":"10.1109\/ICCV.2017.593"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: Activitynet: A large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"7_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"7_CR5","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, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"7_CR6","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, pp. 1130\u20131139 (2018)","DOI":"10.1109\/CVPR.2018.00124"},{"key":"7_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Cao, Q., Zhong, Y., Zhang, J., Gao, S., Tao, D.: Dearkd: data-efficient early knowledge distillation for vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12052\u201312062 (2022)","DOI":"10.1109\/CVPR52688.2022.01174"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: Tood: task-aligned one-stage object detection. arXiv preprint. arXiv:2108.07755 (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"7_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/978-3-030-01216-8_5","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Gao","year":"2018","unstructured":"Gao, J., Chen, K., Nevatia, R.: CTAP: complementary temporal action proposal generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 70\u201385. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_5"},{"key":"7_CR12","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, pp. 3628\u20133636 (2017)","DOI":"10.1109\/ICCV.2017.392"},{"key":"7_CR13","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics, pp. 297\u2013304. JMLR Workshop and Conference Proceedings (2010)"},{"key":"7_CR14","unstructured":"Jiang, Y.G., et al.: THUMOS challenge: action recognition with a large number of classes (2014)"},{"issue":"1\u20132","key":"7_CR15","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Naval Res. Logistics Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logistics Q."},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Lin, C., et al.: Fast learning of temporal action proposal via dense boundary generator. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11499\u201311506 (2020)","DOI":"10.1609\/aaai.v34i07.6815"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Lin, C., et al.: Learning salient boundary feature for anchor-free temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3320\u20133329 (2021)","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"7_CR18","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\/CVF International Conference on Computer Vision, pp. 3889\u20133898 (2019)","DOI":"10.1109\/ICCV.2019.00399"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Shou, Z.: Single shot temporal action detection. In: Proceedings of the 25th ACM international conference on Multimedia, pp. 988\u2013996 (2017)","DOI":"10.1145\/3123266.3123343"},{"key":"7_CR20","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":"7_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Liu, X., Wang, Q., Hu, Y., Tang, X., Bai, S., Bai, X.: End-to-end temporal action detection with transformer. arXiv preprint. arXiv:2106.10271 (2021)","DOI":"10.1109\/TIP.2022.3195321"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"7_CR24","unstructured":"Liu, Z., et al.: Video swin transformer. arXiv preprint. arXiv:2106.13230 (2021)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Long, F., Yao, T., Qiu, Z., Tian, X., Luo, J., Mei, T.: Gaussian temporal awareness networks for action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 344\u2013353 (2019)","DOI":"10.1109\/CVPR.2019.00043"},{"key":"7_CR26","unstructured":"Van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv e-prints, pp. arXiv-1807 (2018)"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Qing, Z., et al.: Temporal context aggregation network for temporal action proposal refinement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 485\u2013494 (2021)","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Sridhar, D., Quader, N., Muralidharan, S., Li, Y., Dai, P., Lu, J.: Class semantics-based attention for action detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13739\u201313748 (2021)","DOI":"10.1109\/ICCV48922.2021.01348"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Tan, J., Tang, J., Wang, L., Wu, G.: Relaxed transformer decoders for direct action proposal generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13526\u201313535 (2021)","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"7_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"11","key":"7_CR33","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Van Gool, L.: Temporal segment networks for action recognition in videos. IEEE Trans. Pattern Anal. Mach. Intell. 41(11), 2740\u20132755 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-c3d: region convolutional 3d network for temporal activity detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5783\u20135792 (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"7_CR35","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10156\u201310165 (2020)","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"7_CR36","unstructured":"Xu, Y., Zhang, Q., Zhang, J., Tao, D.: Vitae: vision transformer advanced by exploring intrinsic inductive bias. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"7_CR37","doi-asserted-by":"publisher","first-page":"8535","DOI":"10.1109\/TIP.2020.3016486","volume":"29","author":"L Yang","year":"2020","unstructured":"Yang, L., Peng, H., Zhang, D., Fu, J., Han, J.: Revisiting anchor mechanisms for temporal action localization. IEEE Trans. Image Process. 29, 8535\u20138548 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Yu, T., Ren, Z., Li, Y., Yan, E., Xu, N., Yuan, J.: Temporal structure mining for weakly supervised action detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5522\u20135531 (2019)","DOI":"10.1109\/ICCV.2019.00562"},{"key":"7_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-540-74936-3_22","volume-title":"Pattern Recognition","author":"C Zach","year":"2007","unstructured":"Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L1 optical flow. In: Hamprecht, F.A., Schn\u00f6rr, C., J\u00e4hne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214\u2013223. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74936-3_22"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Zeng, R., et al.: Graph convolutional networks for temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7094\u20137103 (2019)","DOI":"10.1109\/ICCV.2019.00719"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Xu, Y., Zhang, J., Tao, D.: Vitaev2: vision transformer advanced by exploring inductive bias for image recognition and beyond. arXiv preprint. arXiv:2202.10108 (2022)","DOI":"10.1007\/s11263-022-01739-w"},{"key":"7_CR42","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\/CVF International Conference on Computer Vision, pp. 13658\u201313667 (2021)","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"7_CR43","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":"7_CR44","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint. arXiv:2010.04159 (2020)"},{"key":"7_CR45","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\/CVF International Conference on Computer Vision, 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\/978-3-031-20080-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,11]],"date-time":"2023-03-11T00:44:16Z","timestamp":1678495456000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20080-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200793","9783031200809"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20080-9_7","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":"3 November 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)"}}]}}