{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:30:21Z","timestamp":1773361821159,"version":"3.50.1"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586034","type":"print"},{"value":"9783030586041","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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58604-1_10","type":"book-chapter","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T22:02:49Z","timestamp":1604354569000},"page":"156-171","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval"],"prefix":"10.1007","author":[{"given":"Minuk","family":"Ma","sequence":"first","affiliation":[]},{"given":"Sunjae","family":"Yoon","sequence":"additional","affiliation":[]},{"given":"Junyeong","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Youngjoon","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Sunghun","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Chang D.","family":"Yoo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. In: Proceedings of SSST@EdMNLP 2014, pp. 103\u2013111. Association for Computational Linguistics (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"10_CR2","unstructured":"Duan, X., Huang, W., Gan, C., Wang, J., Zhu, W., Huang, J.: Weakly supervised dense event captioning in videos. In: Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, pp. 3063\u20133073 (2018)"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: TALL: temporal activity localization via language query. In: IEEE International Conference on Computer Vision, ICCV 2017, pp. 5277\u20135285. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: Cascaded boundary regression for temporal action detection. In: British Machine Vision Conference 2017, BMVC 2017. BMVA Press (2017)","DOI":"10.5244\/C.31.52"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Gao, P., et al.: Dynamic fusion with intra- and inter-modality attention flow for visual question answering. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, pp. 6639\u20136648. Computer Vision Foundation\/IEEE (2019)","DOI":"10.1109\/CVPR.2019.00680"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.C.: Localizing moments in video with natural language. In: IEEE International Conference on Computer Vision, ICCV 2017, pp. 5804\u20135813. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K., Darrell, T.: Natural language object retrieval. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4555\u20134564 (2016)","DOI":"10.1109\/CVPR.2016.493"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Li, F.: Large-scale video classification with convolutional neural networks. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, pp. 1725\u20131732. IEEE Computer Society (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Kim, J., Ma, M., Pham, T., Kim, K., Yoo, C.D.: Modality shifting attention network for multi-modal video question answering. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01012"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Klein, B., Lev, G., Sadeh, G., Wolf, L.: Associating neural word embeddings with deep image representations using fisher vectors. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4437\u20134446 (2015)","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"10_CR11","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":"10_CR12","unstructured":"Lin, Z., Zhao, Z., Zhang, Z., Wang, Q., Liu, H.: Weakly-supervised video moment retrieval via semantic completion network. CoRR abs\/1911.08199 (2019). http:\/\/arxiv.org\/abs\/1911.08199"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Weakly supervised temporal action localization through contrast based evaluation networks. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00400"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Mithun, N.C., Paul, S., Roy-Chowdhury, A.K.: Weakly supervised video moment retrieval from text queries. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, pp. 11592\u201311601. Computer Vision Foundation\/IEEE (2019)","DOI":"10.1109\/CVPR.2019.01186"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Liu, T., Prasad, G., Han, B.: Weakly supervised action localization by sparse temporal pooling network. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, pp. 6752\u20136761. IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00706"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Moschitti, A., Pang, B., Daelemans, W. (eds.) Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, pp. 1532\u20131543. ACL (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"10_CR17","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":"10_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"10_CR19","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015 (2015)"},{"key":"10_CR20","unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Proceedings of the 12th International Conference on Neural Information Processing Systems, pp. 1057\u20131063. MIT Press (1999)"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: 2015 IEEE International Conference on Computer Vision, ICCV 2015, pp. 4489\u20134497. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Lin, D., Gool, L.V.: UntrimmedNets for weakly supervised action recognition and detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, pp. 6402\u20136411. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.678"},{"key":"10_CR23","unstructured":"Xu, H., He, K., Sigal, L., Sclaroff, S., Saenko, K.: Text-to-clip video retrieval with early fusion and re-captioning. ArXiv abs\/1804.05113 (2018)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, pp. 6281\u20136290. Computer Vision Foundation\/IEEE (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, D., Dai, X., Wang, X., Wang, Y., Davis, L.S.: MAN: moment alignment network for natural language moment retrieval via iterative graph adjustment. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, pp. 1247\u20131257. Computer Vision Foundation\/IEEE (2019)","DOI":"10.1109\/CVPR.2019.00134"},{"issue":"1","key":"10_CR26","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/s11263-019-01211-2","volume":"128","author":"Y Zhao","year":"2020","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. Int. J. Comput. Vision 128(1), 74\u201395 (2020)","journal-title":"Int. J. Comput. Vision"}],"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\/978-3-030-58604-1_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:10:28Z","timestamp":1730506228000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58604-1_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586034","9783030586041"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58604-1_10","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":"3 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)"}}]}}