{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:44:27Z","timestamp":1777657467520,"version":"3.51.4"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198298","type":"print"},{"value":"9783031198304","type":"electronic"}],"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\/978-3-031-19830-4_41","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T16:21:10Z","timestamp":1666369270000},"page":"724-740","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Video Activity Localisation with\u00a0Uncertainties in\u00a0Temporal Boundary"],"prefix":"10.1007","author":[{"given":"Jiabo","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hailin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaogang","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"41_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 (ICCV), pp. 5803\u20135812 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"41_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of the International Conference on Learning Representations (ICLR) (2015)"},{"key":"41_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 (CVPR), pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"41_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Chen, X., Ma, L., Jie, Z., Chua, T.S.: Temporally grounding natural sentence in video. In: Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 162\u2013171 (2018)","DOI":"10.18653\/v1\/D18-1015"},{"key":"41_CR5","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 (ICCV), pp. 5267\u20135275 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"41_CR6","doi-asserted-by":"crossref","unstructured":"Ge, R., Gao, J., Chen, K., Nevatia, R.: MAC: mining activity concepts for language-based temporal localization. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 245\u2013253. IEEE (2019)","DOI":"10.1109\/WACV.2019.00032"},{"key":"41_CR7","unstructured":"Ghosh, S., Agarwal, A., Parekh, Z., Hauptmann, A.: ExCL: extractive Clip Localization Using Natural Language Descriptions. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 1984\u20131990. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/www.aclweb.org\/anthology\/N19-1198"},{"key":"41_CR8","doi-asserted-by":"publisher","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 (CVPR), pp. 961\u2013970 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298698","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"41_CR9","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":"41_CR10","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Niebles, J.C.: Dense-captioning events in videos. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"Li, K., Guo, D., Wang, M.: Proposal-free video grounding with contextual pyramid network. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 35, pp. 1902\u20131910 (2021)","DOI":"10.1609\/aaai.v35i3.16285"},{"key":"41_CR12","unstructured":"Otani, M., Nakahima, Y., Rahtu, E., Heikkil\u00e4, J.: Uncovering hidden challenges in query-based video moment retrieval. In: Proceedings of the British Machine Vision Conference (BMVC) (2020)"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"Mun, J., Cho, M., Han, B.: Local-global video-text interactions for temporal grounding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10810\u201310819 (2020)","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Nan, G., et al.: Interventional video grounding with dual contrastive learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2765\u20132775 (2021)","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014). https:\/\/www.aclweb.org\/anthology\/D14-1162","DOI":"10.3115\/v1\/D14-1162"},{"key":"41_CR16","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1162\/tacl_a_00207","volume":"1","author":"M Regneri","year":"2013","unstructured":"Regneri, M., Rohrbach, M., Wetzel, D., Thater, S., Schiele, B., Pinkal, M.: Grounding action descriptions in videos. Trans. Assoc.Comput. Linguist. 1, 25\u201336 (2013)","journal-title":"Trans. Assoc.Comput. Linguist."},{"key":"41_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1007\/978-3-642-33718-5_11","volume-title":"Computer Vision \u2013 ECCV 2012","author":"M Rohrbach","year":"2012","unstructured":"Rohrbach, M., Regneri, M., Andriluka, M., Amin, S., Pinkal, M., Schiele, B.: Script data for attribute-based recognition of composite activities. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 144\u2013157. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33718-5_11"},{"key":"41_CR18","unstructured":"Seo, M., Kembhavi, A., Farhadi, A., Hajishirzi, H.: Bidirectional attention flow for machine comprehension. arXiv preprint arXiv:1611.01603 (2016)"},{"key":"41_CR19","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":"41_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), pp. 5998\u20136008 (2017)"},{"key":"41_CR21","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 ACM International Conference on Multimedia (MM), pp. 4116\u20134124 (2020)","DOI":"10.1145\/3394171.3413975"},{"key":"41_CR22","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 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7026\u20137035 (2021)","DOI":"10.1109\/CVPR46437.2021.00695"},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"Xiao, S., et al.: Boundary proposal network for two-stage natural language video localization. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 35, pp. 2986\u20132994 (2021)","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"41_CR24","unstructured":"Xiong, C., Zhong, V., Socher, R.: Dynamic coattention networks for question answering. arXiv preprint arXiv:1611.01604 (2016)"},{"key":"41_CR25","unstructured":"Yu, A.W., Dohan, D., Le, Q., Luong, T., Zhao, R., Chen, K.: Fast and accurate reading comprehension by combining self-attention and convolution. In: Proceedings of the International Conference on Learning Representations (ICLR), vol. 2 (2018)"},{"key":"41_CR26","unstructured":"Yuan, Y., Ma, L., Wang, J., Liu, W., Zhu, W.: Semantic conditioned dynamic modulation for temporal sentence grounding in videos. In: Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), pp. 534\u2013544 (2019)"},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Zeng, R., Xu, H., Huang, W., Chen, P., Tan, M., Gan, C.: Dense regression network for video grounding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10287\u201310296 (2020)","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"41_CR28","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. pp. 6543\u20136554. Association for Computational Linguistics, Online (2020). https:\/\/www.aclweb.org\/anthology\/2020.acl-main.585","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"41_CR29","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 (AAAI), vol. 34, pp. 12870\u201312877 (2020)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"41_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, S., Su, J., Luo, J.: Exploiting temporal relationships in video moment localization with natural language. In: Proceedings of the ACM International Conference on Multimedia (MM), pp. 1230\u20131238 (2019)","DOI":"10.1145\/3343031.3350879"},{"key":"41_CR31","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 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4197\u20134206 (2021)","DOI":"10.1109\/CVPR46437.2021.00418"},{"key":"41_CR32","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":"41_CR33","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 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8445\u20138454 (2021)","DOI":"10.1109\/CVPR46437.2021.00834"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19830-4_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T00:04:56Z","timestamp":1666397096000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19830-4_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198298","9783031198304"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19830-4_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","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":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}