{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:47:00Z","timestamp":1743029220607,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030880125"},{"type":"electronic","value":"9783030880132"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-88013-2_38","type":"book-chapter","created":{"date-parts":[[2021,10,21]],"date-time":"2021-10-21T23:06:25Z","timestamp":1634857585000},"page":"459-471","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Feature Matching Network for Weakly-Supervised Temporal Action Localization"],"prefix":"10.1007","author":[{"given":"Peng","family":"Dou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongke","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,22]]},"reference":[{"key":"38_CR1","doi-asserted-by":"crossref","unstructured":"Buch, S., Escorcia, V., Ghanem, B., Fei-Fei, L., Niebles, J.C.: End-to-end, single-stream temporal action detection in untrimmed videos. In: Procedings of the British Machine Vision Conference 2017. British Machine Vision Association (2019)","DOI":"10.5244\/C.31.93"},{"key":"38_CR2","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":"38_CR3","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":"38_CR4","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":"38_CR5","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Idrees, H., et al.: The THUMOS challenge on action recognition for videos \u201cin the wild.\" Comput. Vis. Image Underst. 155, 1\u201323 (2017)","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Islam, A., Long, C., Radke, R.: A hybrid attention mechanism for weakly-supervised temporal action localization. arXiv preprint arXiv:2101.00545 (2021)","DOI":"10.1109\/WACV45572.2020.9093620"},{"key":"38_CR8","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"38_CR9","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Kumar Singh, K., Jae Lee, Y.: Hide-and-seek: forcing a network to be meticulous for weakly-supervised object and action localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3524\u20133533 (2017)","DOI":"10.1109\/ICCV.2017.381"},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"Lee, P., Uh, Y., Byun, H.: Background suppression network for weakly-supervised temporal action localization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11320\u201311327 (2020)","DOI":"10.1609\/aaai.v34i07.6793"},{"key":"38_CR12","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":"38_CR13","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":"38_CR14","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":"38_CR15","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":"38_CR16","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":"38_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1007\/978-3-030-58526-6_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Luo","year":"2020","unstructured":"Luo, Z., et al.: Weakly-supervised action localization with expectation-maximization multi-instance learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 729\u2013745. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58526-6_43"},{"key":"38_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/978-3-030-58568-6_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Min","year":"2020","unstructured":"Min, K., Corso, J.J.: Adversarial background-aware loss for weakly-supervised temporal activity localization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 283\u2013299. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_17"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Narayan, S., Cholakkal, H., Khan, F.S., Shao, L.: 3C-Net: category count and center loss for weakly-supervised action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8679\u20138687 (2019)","DOI":"10.1109\/ICCV.2019.00877"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Liu, T., Prasad, G., Han, B.: Weakly supervised action localization by sparse temporal pooling network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6752\u20136761 (2018)","DOI":"10.1109\/CVPR.2018.00706"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Nguyen, P.X., Ramanan, D., Fowlkes, C.C.: Weakly-supervised action localization with background modeling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5502\u20135511 (2019)","DOI":"10.1109\/ICCV.2019.00560"},{"key":"38_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1007\/978-3-030-01225-0_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Paul","year":"2018","unstructured":"Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-TALC: weakly-supervised temporal activity localization and classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 588\u2013607. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_35"},{"key":"38_CR23","doi-asserted-by":"crossref","unstructured":"Shi, B., Dai, Q., Mu, Y., Wang, J.: Weakly-supervised action localization by generative attention modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1009\u20131019 (2020)","DOI":"10.1109\/CVPR42600.2020.00109"},{"key":"38_CR24","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, pp. 5734\u20135743 (2017)","DOI":"10.1109\/CVPR.2017.155"},{"key":"38_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1007\/978-3-030-01270-0_10","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Shou","year":"2018","unstructured":"Shou, Z., Gao, H., Zhang, L., Miyazawa, K., Chang, S.-F.: AutoLoc: weakly-supervised temporal action localization in untrimmed videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 162\u2013179. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_10"},{"key":"38_CR26","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, pp. 1049\u20131058 (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"38_CR27","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Lin, D., Van Gool, L.: Untrimmednets for weakly supervised action recognition and detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4325\u20134334 (2017)","DOI":"10.1109\/CVPR.2017.678"},{"key":"38_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/978-3-642-03061-1_2","volume-title":"Statistical and Geometrical Approaches to Visual Motion Analysis","author":"A Wedel","year":"2009","unstructured":"Wedel, A., Pock, T., Zach, C., Bischof, H., Cremers, D.: An improved algorithm for TV-$$L^{1}$$ optical flow. In: Cremers, D., Rosenhahn, B., Yuille, A.L., Schmidt, F.R. (eds.) Statistical and Geometrical Approaches to Visual Motion Analysis. LNCS, vol. 5604, pp. 23\u201345. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-03061-1_2"},{"key":"38_CR29","unstructured":"Xiong, Y., Zhao, Y., Wang, L., Lin, D., Tang, X.: A pursuit of temporal accuracy in general activity detection. arXiv preprint arXiv:1703.02716 (2017)"},{"key":"38_CR30","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":"38_CR31","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":"38_CR32","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":"38_CR33","doi-asserted-by":"crossref","unstructured":"Yuan, J., Ni, B., Yang, X., Kassim, A.A.: Temporal action localization with pyramid of score distribution features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3093\u20133102 (2016)","DOI":"10.1109\/CVPR.2016.337"},{"key":"38_CR34","unstructured":"Yuan, Y., Lyu, Y., Shen, X., Tsang, I.W., Yeung, D.Y.: Marginalized average attentional network for weakly-supervised learning. arXiv preprint arXiv:1905.08586 (2019)"},{"issue":"12","key":"38_CR35","doi-asserted-by":"publisher","first-page":"5797","DOI":"10.1109\/TIP.2019.2922108","volume":"28","author":"R Zeng","year":"2019","unstructured":"Zeng, R., Gan, C., Chen, P., Huang, W., Wu, Q., Tan, M.: Breaking winner-takes-all: iterative-winners-out networks for weakly supervised temporal action localization. IEEE Trans. Image Process. 28(12), 5797\u20135808 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"38_CR36","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":"38_CR37","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":"38_CR38","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, pp. 2914\u20132923 (2017)","DOI":"10.1109\/ICCV.2017.317"},{"key":"38_CR39","unstructured":"Zhou, Z.H.: Multi-instance learning: a survey. Technical report, Department of Computer Science & Technology, Nanjing University, 2 (2004)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-88013-2_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,22]],"date-time":"2021-10-22T00:22:39Z","timestamp":1634862159000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-88013-2_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030880125","9783030880132"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-88013-2_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.prcv.cn\/2021\/index_en.html","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":"513","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":"201","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":"39% - 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":"5","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":"There were 30 oral and 171 poster presentations at the conference.","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)"}}]}}