{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:05:32Z","timestamp":1761897932976,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":49,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819720910"},{"type":"electronic","value":"9789819720927"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-2092-7_14","type":"book-chapter","created":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T06:02:18Z","timestamp":1711692138000},"page":"281-301","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Denoised Dual-Level Contrastive Network for\u00a0Weakly-Supervised Temporal Sentence Grounding"],"prefix":"10.1007","author":[{"given":"Yaru","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haichao","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,30]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Anne\u00a0Hendricks, L., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5803\u20135812 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Caba\u00a0Heilbron, F., Escorcia, V., Ghanem, B., Carlos\u00a0Niebles, 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":"14_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-030-01264-9_9","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Caron","year":"2018","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 139\u2013156. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_9"},{"key":"14_CR4","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":"14_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., Luo, W., Zhang, W., Ma, L.: Explore inter-contrast between videos via composition for weakly supervised temporal sentence grounding 36(01), 267\u2013275 (2022)","DOI":"10.1609\/aaai.v36i1.19902"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Chen, X., Ma, L., Jie, Z., Chua, T.S.: Temporally grounding natural sentence in video. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 162\u2013171 (2018)","DOI":"10.18653\/v1\/D18-1015"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Chen, S., Jiang, Y.G.: Towards bridging event captioner and sentence localizer for weakly supervised dense event captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8425\u20138435 (2021)","DOI":"10.1109\/CVPR46437.2021.00832"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Ma, L., Luo, W., Tang, P., Wong, K.Y.K.: Look closer to ground better: Weakly-supervised temporal grounding of sentence in video. arXiv preprint arXiv:2001.09308 (2020)","DOI":"10.18653\/v1\/P19-1183"},{"issue":"1\u201368","key":"14_CR10","first-page":"1","volume":"2000","author":"RT Collins","year":"2000","unstructured":"Collins, R.T., et al.: A system for video surveillance and monitoring. Vsam Final Report 2000(1\u201368), 1 (2000)","journal-title":"Vsam Final Report"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Da, C., Zhang, Y., Zheng, Y., Pan, P., Xu, Y., Pan, C.: Asynce: disentangling false-positives for weakly-supervised video grounding. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1129\u20131137 (2021)","DOI":"10.1145\/3474085.3481539"},{"key":"14_CR12","unstructured":"Duan, X., et al.: Weakly supervised dense event captioning in videos. Adv. Neural. Inf. Process. Syst. 31 (2018)"},{"key":"14_CR13","unstructured":"Fang, Z., Kong, S., Wang, Z., Fowlkes, C., Yang, Y.: Weak supervision and referring attention for temporal-textual association learning. arXiv preprint arXiv:2006.11747 (2020)"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: Tall: temporal activity localization via language query. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5267\u20135275 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Gao, M., Davis, L.S., Socher, R., Xiong, C.: Wslln: weakly supervised natural language localization networks. arXiv preprint arXiv:1909.00239 (2019)","DOI":"10.18653\/v1\/D19-1157"},{"key":"14_CR16","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Islam, A., Radke, R.: Weakly supervised temporal action localization using deep metric learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 547\u2013556 (2020)","DOI":"10.1109\/WACV45572.2020.9093620"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"14_CR19","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Carlos\u00a0Niebles, J.: Dense-captioning events in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 706\u2013715 (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Lin, Z., Zhao, Z., Zhang, Z., Wang, Q., Liu, H.: Weakly-supervised video moment retrieval via semantic completion network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11539\u201311546 (2020)","DOI":"10.1609\/aaai.v34i07.6820"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Loper, E., Bird, S.: Nltk: The natural language toolkit. arXiv preprint cs\/0205028 (2002)","DOI":"10.3115\/1118108.1118117"},{"key":"14_CR23","unstructured":"Luo, F., Chen, S., Chen, J., Wu, Z., Jiang, Y.G.: Self-supervised learning for semi-supervised temporal language grounding. arXiv preprint arXiv:2109.11475 (2021)"},{"key":"14_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/978-3-030-58604-1_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Ma","year":"2020","unstructured":"Ma, M., Yoon, S., Kim, J., Lee, Y., Kang, S., Yoo, C.D.: VLANet: video-language alignment network for weakly-supervised video moment retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 156\u2013171. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_10"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Ma, Y.F., Lu, L., Zhang, H.J., Li, M.: A user attention model for video summarization. In: Proceedings of the Tenth ACM International Conference on Multimedia, pp. 533\u2013542 (2002)","DOI":"10.1145\/641007.641116"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Mithun, N.C., Paul, S., Roy-Chowdhury, A.K.: Weakly supervised video moment retrieval from text queries. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11592\u201311601 (2019)","DOI":"10.1109\/CVPR.2019.01186"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Nam, J., Ahn, D., Kang, D., Ha, S.J., Choi, J.: Zero-shot natural language video localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1470\u20131479 (2021)","DOI":"10.1109\/ICCV48922.2021.00150"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Pan, T., Song, Y., Yang, T., Jiang, W., Liu, W.: Videomoco: contrastive video representation learning with temporally adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11205\u201311214 (2021)","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"14_CR30","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":"14_CR31","unstructured":"Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. Adv. Neural Inform. Process. Syst. 29 (2016)"},{"key":"14_CR32","unstructured":"Song, Y., Wang, J., Ma, L., Yu, Z., Yu, J.: Weakly-supervised multi-level attentional reconstruction network for grounding textual queries in videos. arXiv preprint arXiv:2003.07048 (2020)"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Tan, R., Xu, H., Saenko, K., Plummer, B.A.: Logan: latent graph co-attention network for weakly-supervised video moment retrieval. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2083\u20132092 (2021)","DOI":"10.1109\/WACV48630.2021.00213"},{"key":"14_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-030-58621-8_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 776\u2013794. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_45"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"14_CR36","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y., Deng, J., Zhou, W., Li, H.: Weakly supervised temporal adjacent network for language grounding. IEEE Trans. Multimedia (2021)","DOI":"10.1109\/TMM.2021.3096087"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhou, W., Li, H.: Fine-grained semantic alignment network for weakly supervised temporal language grounding. arXiv preprint arXiv:2210.11933 (2022)","DOI":"10.18653\/v1\/2021.findings-emnlp.9"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chen, J., Jiang, Y.G.: Visual co-occurrence alignment learning for weakly-supervised video moment retrieval. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1459\u20131468 (2021)","DOI":"10.1145\/3474085.3475278"},{"key":"14_CR40","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3733\u20133742 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Xu, H., He, K., Plummer, B.A., Sigal, L., Sclaroff, S., Saenko, K.: Multilevel language and vision integration for text-to-clip retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 9062\u20139069 (2019)","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"14_CR42","unstructured":"Xu, Y., Cao, P., Kong, Y., Wang, Y.: L_dmi: A novel information-theoretic loss function for training deep nets robust to label noise. Adv. Neural Inform. Process. Syst. 32 (2019)"},{"key":"14_CR43","doi-asserted-by":"publisher","first-page":"3252","DOI":"10.1109\/TIP.2021.3058614","volume":"30","author":"W Yang","year":"2021","unstructured":"Yang, W., Zhang, T., Zhang, Y., Wu, F.: Local correspondence network for weakly supervised temporal sentence grounding. IEEE Trans. Image Process. 30, 3252\u20133262 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Mei, T., Zhu, W.: To find where you talk: temporal sentence localization in video with attention based location regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 9159\u20139166 (2019)","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, S., Peng, H., Fu, J., Luo, J.: Learning 2d temporal adjacent networks for moment localization with natural language. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 12870\u201312877 (2020)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"14_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Lin, Z., Zhao, Z., Zhu, J., He, X.: Regularized two-branch proposal networks for weakly-supervised moment retrieval in videos. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 4098\u20134106 (2020)","DOI":"10.1145\/3394171.3413967"},{"key":"14_CR47","first-page":"18123","volume":"33","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Zhao, Z., Lin, Z., He, X., et al.: Counterfactual contrastive learning for weakly-supervised vision-language grounding. Adv. Neural. Inf. Process. Syst. 33, 18123\u201318134 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR48","doi-asserted-by":"crossref","unstructured":"Zheng, M., Huang, Y., Chen, Q., Liu, Y.: Weakly supervised video moment localization with contrastive negative sample mining. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a01, p.\u00a03 (2022)","DOI":"10.1609\/aaai.v36i3.20263"},{"key":"14_CR49","doi-asserted-by":"crossref","unstructured":"Zheng, M., Huang, Y., Chen, Q., Peng, Y., Liu, Y.: Weakly supervised temporal sentence grounding with gaussian-based contrastive proposal learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15555\u201315564 (2022)","DOI":"10.1109\/CVPR52688.2022.01511"}],"container-title":["Lecture Notes in Computer Science","Computational Visual Media"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2092-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T06:06:51Z","timestamp":1711692411000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2092-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819720910","9789819720927"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2092-7_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"30 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Visual Media","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 April 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 April 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvm2024","order":10,"name":"conference_id","label":"Conference ID","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":"CVM submission system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"212","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":"34","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":"16% - 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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}