{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:51:17Z","timestamp":1742914277042,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":44,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819984282"},{"type":"electronic","value":"9789819984299"}],"license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"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\/978-981-99-8429-9_36","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"446-460","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Contrastive Perturbation Network for\u00a0Weakly Supervised Temporal Sentence Grounding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2131-9200","authenticated-orcid":false,"given":"Tingting","family":"Han","sequence":"first","affiliation":[]},{"given":"Yuanxin","family":"Lv","sequence":"additional","affiliation":[]},{"given":"Zhou","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Jianping","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Liu","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Anne Hendricks, 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":"36_CR2","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":"36_CR3","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":"36_CR4","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":"36_CR5","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"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Ma, L., Luo, W., Wong, K.Y.K.: Weakly-supervised spatio-temporally grounding natural sentence in video. arXiv preprint arXiv:1906.02549 (2019)","DOI":"10.18653\/v1\/P19-1183"},{"key":"36_CR7","unstructured":"Collins, R.T., et al.: A system for video surveillance and monitoring. VSAM Final Report 2000(1\u201368), 1 (2000)"},{"key":"36_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"36_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"36_CR10","unstructured":"Duan, X., Huang, W., Gan, C., Wang, J., Zhu, W., Huang, J.: Weakly supervised dense event captioning in videos. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"36_CR11","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":"36_CR12","doi-asserted-by":"crossref","unstructured":"Foroughi, H., Aski, B.S., Pourreza, H.: Intelligent video surveillance for monitoring fall detection of elderly in home environments. In: 2008 11th International Conference on Computer and Information Technology, pp. 219\u2013224. IEEE (2008)","DOI":"10.1109\/ICCITECHN.2008.4803020"},{"key":"36_CR13","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":"36_CR14","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":"36_CR15","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: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 961\u2013970. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"36_CR16","doi-asserted-by":"crossref","unstructured":"Huang, J., Liu, Y., Gong, S., Jin, H.: Cross-sentence temporal and semantic relations in video activity localisation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7199\u20137208 (2021)","DOI":"10.1109\/ICCV48922.2021.00711"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Carlos Niebles, 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":"36_CR18","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. 34, pp. 11539\u201311546 (2020)","DOI":"10.1609\/aaai.v34i07.6820"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Luo, F., Chen, S., Chen, J., Wu, Z., Jiang, Y.G.: Self-supervised learning for semi-supervised temporal language grounding. IEEE Trans. Multim. (2022)","DOI":"10.1109\/TMM.2022.3228167"},{"key":"36_CR20","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-030-58604-1_10"},{"key":"36_CR21","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":"36_CR22","unstructured":"Narasimhan, M., Rohrbach, A., Darrell, T.: Clip-it! language-guided video summarization. In: Advances in Neural Information Processing Systems, pp. 13988\u201314000 (2021)"},{"key":"36_CR23","unstructured":"Otani, M., Nakashima, Y., Rahtu, E., Heikkil\u00e4, J.: Uncovering hidden challenges in query-based video moment retrieval. arXiv preprint arXiv:2009.00325 (2020)"},{"key":"36_CR24","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"},{"issue":"4","key":"36_CR25","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1007\/s00521-016-2525-z","volume":"29","author":"J Singha","year":"2018","unstructured":"Singha, J., Roy, A., Laskar, R.H.: Dynamic hand gesture recognition using vision-based approach for human-computer interaction. Neural Comput. Appl. 29(4), 1129\u20131141 (2018)","journal-title":"Neural Comput. Appl."},{"key":"36_CR26","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":"36_CR27","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":"36_CR28","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":"36_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"36_CR30","doi-asserted-by":"crossref","unstructured":"Wang, H., Zha, Z.J., Chen, X., Xiong, Z., Luo, J.: Dual path interaction network for video moment localization. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 4116\u20134124 (2020)","DOI":"10.1145\/3394171.3413975"},{"key":"36_CR31","doi-asserted-by":"crossref","unstructured":"Wang, H., Zha, Z.J., Li, L., Liu, D., Luo, J.: Structured multi-level interaction network for video moment localization via language query. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7026\u20137035 (2021)","DOI":"10.1109\/CVPR46437.2021.00695"},{"key":"36_CR32","doi-asserted-by":"publisher","first-page":"3276","DOI":"10.1109\/TMM.2021.3096087","volume":"24","author":"Y Wang","year":"2021","unstructured":"Wang, Y., Deng, J., Zhou, W., Li, H.: Weakly supervised temporal adjacent network for language grounding. IEEE Trans. Multim. 24, 3276\u20133286 (2021)","journal-title":"IEEE Trans. Multim."},{"key":"36_CR33","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":"36_CR34","doi-asserted-by":"crossref","unstructured":"Wu, J., Li, G., Han, X., Lin, L.: Reinforcement learning for weakly supervised temporal grounding of natural language in untrimmed videos. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1283\u20131291 (2020)","DOI":"10.1145\/3394171.3413862"},{"key":"36_CR35","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. 33, pp. 9062\u20139069 (2019)","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"36_CR36","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":"36_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, D., Dai, X., Wang, X., Wang, Y.F., Davis, L.S.: Man: moment alignment network for natural language moment retrieval via iterative graph adjustment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1247\u20131257 (2019)","DOI":"10.1109\/CVPR.2019.00134"},{"key":"36_CR38","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. 34, pp. 12870\u201312877 (2020)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"36_CR39","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":"36_CR40","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":"36_CR41","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhao, Z., Zhang, Z., Lin, Z.: Cascaded prediction network via segment tree for temporal video grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4197\u20134206 (2021)","DOI":"10.1109\/CVPR46437.2021.00418"},{"key":"36_CR42","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. 36, pp. 3517\u20133525 (2022)","DOI":"10.1609\/aaai.v36i3.20263"},{"key":"36_CR43","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"},{"key":"36_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhang, C., Luo, Y., Chen, Y., Hu, C.: Embracing uncertainty: decoupling and de-bias for robust temporal grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8445\u20138454 (2021)","DOI":"10.1109\/CVPR46437.2021.00834"}],"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\/978-981-99-8429-9_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:21:26Z","timestamp":1703319686000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8429-9_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984282","9789819984299"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8429-9_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,24]]},"assertion":[{"value":"24 December 2023","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":"Xiamen","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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)"}}]}}