{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:00:17Z","timestamp":1786978817768,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585389","type":"print"},{"value":"9783030585396","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58539-6_3","type":"book-chapter","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T14:02:46Z","timestamp":1604671366000},"page":"37-54","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":117,"title":["Two-Stream Consensus Network for\u00a0Weakly-Supervised Temporal Action\u00a0Localization"],"prefix":"10.1007","author":[{"given":"Yuanhao","family":"Zhai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qilin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Hua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,7]]},"reference":[{"key":"3_CR1","unstructured":"Alwassel, H., Pardo, A., Heilbron, F.C., Thabet, A., Ghanem, B.: RefineLoc: iterative refinement for weakly-supervised action localization. arXiv preprint arXiv:1904.00227 (2019)"},{"key":"3_CR2","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, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"3_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":"3_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":"3_CR5","doi-asserted-by":"crossref","unstructured":"Crasto, N., Weinzaepfel, P., Alahari, K., Schmid, C.: MARS: motion-augmented RGB stream for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7882\u20137891 (2019)","DOI":"10.1109\/CVPR.2019.00807"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Dai, X., Singh, B., Zhang, G., Davis, L.S., Chen, Y.Q.: Temporal context network for activity localization in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5793\u20135802 (2017)","DOI":"10.1109\/ICCV.2017.610"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 886\u2013893 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: Proceedings of the European Conference on Computer Vision, pp. 428\u2013441 (2006)","DOI":"10.1007\/11744047_33"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Li, F.F.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3_CR10","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":"3_CR11","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":"3_CR12","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: Cascaded boundary regression for temporal action detection. arXiv preprint arXiv:1705.01180 (2017)","DOI":"10.5244\/C.31.52"},{"key":"3_CR13","unstructured":"Gorban, A., et al.: THUMOS challenge: action recognition with a large number of classes (2015)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Barrios, W., Escorcia, V., Ghanem, B.: SCC: semantic context cascade for efficient action detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3175\u20133184 (2017)","DOI":"10.1109\/CVPR.2017.338"},{"key":"3_CR15","unstructured":"Jiang, Y.G., et al.: THUMOS challenge: action recognition with a large number of classes (2014)"},{"key":"3_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"3_CR17","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Singh, K.K., Lee, Y.J.: 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":"3_CR19","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I.: On space-time interest points. Int. J. Comput. Vis. 64, 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR20","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 (2020)","DOI":"10.1609\/aaai.v34i07.6793"},{"key":"3_CR21","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, pp. 3889\u20133898 (2019)","DOI":"10.1109\/ICCV.2019.00399"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: boundary sensitive network for temporal action proposal generation. In: Proceedings of the European Conference on Computer Vision, pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Liu, D., Jiang, T., Wang, Y.: Completeness modeling and context separation for weakly supervised temporal action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1298\u20131307 (2019)","DOI":"10.1109\/CVPR.2019.00139"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Weakly supervised temporal action localization through contrast based evaluation networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3899\u20133908 (2019)","DOI":"10.1109\/ICCV.2019.00400"},{"key":"3_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 Conference on Computer Vision and Pattern Recognition, pp. 344\u2013353 (2019)","DOI":"10.1109\/CVPR.2019.00043"},{"key":"3_CR26","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 International Conference on Computer Vision, pp. 8679\u20138687 (2019)","DOI":"10.1109\/ICCV.2019.00877"},{"key":"3_CR27","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":"3_CR28","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 International Conference on Computer Vision, pp. 5502\u20135511 (2019)","DOI":"10.1109\/ICCV.2019.00560"},{"key":"3_CR29","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8024\u20138035 (2019)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-TALC: weakly-supervised temporal activity localization and classification. In: Proceedings of the European Conference on Computer Vision, pp. 563\u2013579 (2018)","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A., Ryoo, M.S.: Representation flow for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.01018"},{"key":"3_CR32","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"3_CR33","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":"3_CR34","doi-asserted-by":"crossref","unstructured":"Shou, Z., Gao, H., Zhang, L., Miyazawa, K., Chang, S.F.: AutoLoc: weakly-supervised temporal action localization in untrimmed videos. In: Proceedings of the European Conference on Computer Vision, pp. 154\u2013171 (2018)","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Shou, Z., et al.: DMC-Net: generating discriminative motion cues for fast compressed video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1268\u20131277 (2019)","DOI":"10.1109\/CVPR.2019.00136"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Proceedings of the European Conference on Computer Vision, pp. 510\u2013526 (2016)","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"3_CR37","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Tan, M., et al.: Learning graph structure for multi-label image classification via clique generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4100\u20134109 (2015)","DOI":"10.1109\/CVPR.2015.7299037"},{"key":"3_CR39","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3169\u20133176 (2011)"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Wang, L., Koniusz, P., Huynh, D.Q.: Hallucinating IDT descriptors and I3D optical flow features for action recognition with CNNS. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8698\u20138708 (2019)","DOI":"10.1109\/ICCV.2019.00879"},{"key":"3_CR41","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":"3_CR42","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":"3_CR43","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 International Conference on Computer Vision, pp. 5522\u20135531 (2019)","DOI":"10.1109\/ICCV.2019.00562"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Stroud, J.C., Lu, T., Deng, J.: Temporal action localization by structured maximal sums. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3684\u20133692 (2017)","DOI":"10.1109\/CVPR.2017.342"},{"key":"3_CR45","unstructured":"Zeng, R., et al.: Graph convolutional networks for temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7094\u20137103 (2019)"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Zhai, Y., Wang, L., Liu, Z., Zhang, Q., Hua, G., Zheng, N.: Action coherence network for weakly supervised temporal action localization. In: Proceedings of the IEEE International Conference on Image Processing, pp. 3696\u20133700 (2019)","DOI":"10.1109\/ICIP.2019.8803447"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Lin, D.: Recognize actions by disentangling components of dynamics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6566\u20136575 (2018)","DOI":"10.1109\/CVPR.2018.00687"},{"key":"3_CR48","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":"3_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58539-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T19:04:53Z","timestamp":1730833493000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58539-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585389","9783030585396"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58539-6_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"7 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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":"The conference was held virtually due to the COVID-19 pandemic.","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)"}}]}}