{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T17:29:49Z","timestamp":1767979789941,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543779","type":"print"},{"value":"9789819543786","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4378-6_14","type":"book-chapter","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T15:53:08Z","timestamp":1762789988000},"page":"196-210","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Event-Driven Surveillance Video Moment Retrieval with\u00a0Foreground Enhancement"],"prefix":"10.1007","author":[{"given":"Shuyi","family":"He","sequence":"first","affiliation":[]},{"given":"Qingchao","family":"Kong","sequence":"additional","affiliation":[]},{"given":"Wenji","family":"Mao","sequence":"additional","affiliation":[]},{"given":"Shaoqiang","family":"Tang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,9]]},"reference":[{"key":"14_CR1","unstructured":"Yuan, T., et al.: Towards surveillance video-and-language understanding: new dataset baselines and challenges. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22\u00a0052\u201322\u00a0061 (2024)"},{"key":"14_CR2","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_CR3","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_CR4","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":"10.18653\/v1\/D18-1168"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Liu, M., Wang, X., Nie, L., Tian, Q., Chen, B., Chua, T.-S.: Cross-modal moment localization in videos. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 843\u2013851 (2018)","DOI":"10.1145\/3240508.3240549"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Ma, L., Wang, J. Liu, W., Zhu, W.: Semantic conditioned dynamic modulation for temporal sentence grounding in videos. Adv. Neural Info. Process. Syst. 32 (2019)","DOI":"10.1109\/TPAMI.2020.3038993"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, D., Dai, X., Wang, X., Wang, Y.-F., Davis, L.\u00a0S.: 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"},{"issue":"01","key":"14_CR8","first-page":"9062","volume":"33","author":"H Xu","year":"2019","unstructured":"Xu, H., He, K., Plummer, B.A., Sigal, L., Sclaroff, S., Saenko, K.: Multilevel language and vision integration for text-to-clip retrieval. Proc. AAAI Conf. Artif. Intell. 33(01), 9062\u20139069 (2019)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"14_CR9","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, no.\u00a007, pp. 12\u00a0870\u201312\u00a0877 (2020)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Wu, Z., Gao, J., Huang, S., Xu, C.: Diving into the relations: leveraging semantic and visual structures for video moment retrieval. In: 2021 IEEE International Conference on Multimedia and Expo (ICME). IEEE, pp. 1\u20136 (2021)","DOI":"10.1109\/ICME51207.2021.9428369"},{"key":"14_CR11","unstructured":"Wang, J., Ma, L., Jiang, W.: Temporally grounding language queries in videos by contextual boundary-aware prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12\u00a0168\u201312\u00a0175 (2020)"},{"issue":"3","key":"14_CR12","first-page":"2613","volume":"36","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Wang, L., Wu, T., Li, T., Wu, G.: Negative sample matters: a renaissance of metric learning for temporal grounding. Proc. AAAI Conf. Artif. Intell. 36(3), 2613\u20132623 (2022)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"01","key":"14_CR13","first-page":"9159","volume":"33","author":"Y Yuan","year":"2019","unstructured":"Yuan, Y., Mei, T., Zhu, W.: To find where you talk: temporal sentence localization in video with attention based location regression. Proc. AAAI Conf. Artif. Intell. 33(01), 9159\u20139166 (2019)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Lu, C., Chen, L., Tan, C., Li, X., Xiao, J.: DEBUG: a dense bottom-up grounding approach for natural language video localization. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 5144\u20135153 (2019)","DOI":"10.18653\/v1\/D19-1518"},{"key":"14_CR15","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. 10\u00a0810\u201310\u00a0819 (2020)","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"14_CR16","unstructured":"Zeng, R., Xu, H., Huang, W., Chen, P., Tan, M., Gan, C.: Dense regression network for video grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10\u00a0287\u201310\u00a0296 (2020)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Zhang, H., Sun, A., Jing, W., Zhou, J.\u00a0T.: 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 (2020)","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"14_CR18","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"},{"key":"14_CR19","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, pp. 1902\u20131910 (2021)","DOI":"10.1609\/aaai.v35i3.16285"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, S., Wu, Y., Chen, C.-W., Shan, Y., Qie, X.: UMT: unified multi-modal transformers for joint video moment retrieval and highlight detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3042\u20133051 (2022)","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"14_CR21","unstructured":"Li, P., et al.: MomentDiff: generative video moment retrieval from random to real. In: Advances in Veural Information Processing Systems, vol.\u00a036, pp. 65\u00a0948\u201365\u00a0966 (2023)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Zhang, W., Zhang, X., Wei, X.-Y., Chen, C.\u00a0W., Li, Q.: Prior knowledge integration via LLM encoding and pseudo event regulation for video moment retrieval. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 7249\u20137258 (2024)","DOI":"10.1145\/3664647.3681115"},{"issue":"01","key":"14_CR23","first-page":"8393","volume":"33","author":"D He","year":"2019","unstructured":"He, D., Zhao, X., Huang, J., Li, F., Liu, X., Wen, S.: Read, watch, and move: reinforcement learning for temporally grounding natural language descriptions in videos. Proc. AAAI Conf. Artif. Intell. 33(01), 8393\u20138400 (2019)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Wang, W., Huang, Y., Wang, L.: Language-driven temporal activity localization: a semantic matching reinforcement learning model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 334\u2013343 (2019)","DOI":"10.1109\/CVPR.2019.00042"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Wu, J., Li, G., Liu, S., Lin, L.: Tree-structured policy based progressive reinforcement learning for temporally language grounding in video. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, no.\u00a007, pp. 12\u00a0386\u201312\u00a0393 (2020)","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"14_CR26","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"},{"issue":"8","key":"14_CR27","first-page":"4252","volume":"44","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Sun, A., Jing, W., Zhen, L., Zhou, J.T., Goh, R.S.M.: Natural language video localization: a revisit in span-based question answering framework. IEEE Trans. Pattern Anal. Mach. Intell. 44(8), 4252\u20134266 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR28","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"14_CR29","unstructured":"Doddington, G.\u00a0R., Mitchell, A., Przybocki, M.\u00a0A., Ramshaw, L.\u00a0A., Strassel, S.\u00a0M., Weischedel, R.\u00a0M. : The automatic content extraction (ACE) program-tasks, data, and evaluation. In : Lrec, vol.\u00a02, no.\u00a01. Lisbon, pp. 837\u2013840 (2004)"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Peng, H., et al.: OmniEvent: a comprehensive, fair, and easy-to-use toolkit for event understanding. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 508\u2013517 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.46"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4378-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T05:59:16Z","timestamp":1767938356000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4378-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,9]]},"ISBN":["9789819543779","9789819543786"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4378-6_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,9]]},"assertion":[{"value":"9 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}