{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:37:56Z","timestamp":1742913476722,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031189067"},{"type":"electronic","value":"9783031189074"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-18907-4_34","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"436-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Synthesizing Counterfactual Samples for\u00a0Overcoming Moment Biases in\u00a0Temporal Video Grounding"],"prefix":"10.1007","author":[{"given":"Mingliang","family":"Zhai","sequence":"first","affiliation":[]},{"given":"Chuanhao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Chenchen","family":"Jing","sequence":"additional","affiliation":[]},{"given":"Yuwei","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"34_CR1","unstructured":"Wang, Z., Wang, L., Wu, T., et al.: Negative sample matters: a renaissance of metric learning for temporal grounding. arXiv preprint arXiv:2109.04872 (2021)"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Mun, J., Cho, M., Han, B.: Local-global video-text interactions for temporal grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10810\u201310819 (2020)","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Li, M., Wang, T., Zhang, H., et al.: End-to-End modeling via information tree for one-shot natural language spatial video grounding. arXiv preprint arXiv:2203.08013 (2022)","DOI":"10.18653\/v1\/2022.acl-long.596"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., et al.: 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":"34_CR5","doi-asserted-by":"crossref","unstructured":"Liu, D., Qu, X., Zhou, P., et al.: Exploring motion and appearance information for temporal sentence grounding. arXiv preprint arXiv:2201.00457 (2022)","DOI":"10.1609\/aaai.v36i2.20059"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Li, J., Xie, J., Qian, L., et al.: Compositional temporal grounding with structured variational cross-graph correspondence learning. arXiv preprint arXiv:2203.13049 (2022)","DOI":"10.1109\/CVPR52688.2022.00304"},{"key":"34_CR7","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":"34_CR8","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, no. 07, pp. 12870\u201312877 (2020)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, H., Sun, A., Jing, W., Zhou, J.T.: Span-based localizing network for natural language video localization. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, pp. 6543\u20136554. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.585","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Ma, L., Wang, J., et al.: Semantic conditioned dynamic modulation for temporal sentence grounding in videos. In: Advances in Neural Information Processing Systems, vol. 32 (2019)","DOI":"10.1109\/TPAMI.2020.3038993"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Lan, X., Wang, X., et al.: A closer look at temporal sentence grounding in videos: dataset and metric. In: Proceedings of the 2nd International Workshop on Human-centric Multimedia Analysis, pp. 13\u201321 (2021)","DOI":"10.1145\/3475723.3484247"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Liu, D., Qu, X., Di, X., Cheng, Y., Xu Xu, Z., Zhou, P.: Memory-guided semantic learning network for temporal sentence grounding. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i2.20058"},{"key":"34_CR13","unstructured":"Zhang, H., Sun, A., Jing, W., Zhou, J.T.: Towards debiasing temporal sentence grounding in video. arXiv preprint arXiv:2111.04321 (2021)"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Yang, X., Feng, F., Ji, W., Wang, M., Chua, T.-S.: Deconfounded video moment retrieval with causal intervention. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 1\u201310 (2021)","DOI":"10.1145\/3404835.3462823"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., et al.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"34_CR16","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":"34_CR17","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., et al.: 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":"34_CR18","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. ICLR"},{"key":"34_CR19","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Yang, X., Feng, F., Ji, W., et al.: Deconfounded video moment retrieval with causal intervention. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1\u201310 (2021)","DOI":"10.1145\/3404835.3462823"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., et al.: 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":"34_CR22","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., et al.: Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"34_CR23","first-page":"18123","volume":"33","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Zhao, Z., Lin, Z., 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":"34_CR24","doi-asserted-by":"crossref","unstructured":"Hirota, Y., Garcia, N., Otani, M., et al.: Visual question answering with textual representations for images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3154\u20133157 (2021)","DOI":"10.1109\/ICCVW54120.2021.00353"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Chen, L., Yan, X., Xiao, J., et al.: Counterfactual samples synthesizing for robust visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10800\u201310809 (2020)","DOI":"10.1109\/CVPR42600.2020.01081"}],"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\/978-3-031-18907-4_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:10:26Z","timestamp":1666825826000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18907-4_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189067","9783031189074"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18907-4_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"27 October 2022","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":"Shenzhen","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.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","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","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":"233","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":"41% - 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":"3.03","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":"3.35","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)"}}]}}