{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:44:12Z","timestamp":1767339852095,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030642204"},{"type":"electronic","value":"9783030642211"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-64221-1_11","type":"book-chapter","created":{"date-parts":[[2020,11,28]],"date-time":"2020-11-28T11:02:33Z","timestamp":1606561353000},"page":"119-129","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Semantic Modulation Based Residual Network for Temporal Language Queries Grounding in Video"],"prefix":"10.1007","author":[{"given":"Cheng","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7096-1830","authenticated-orcid":false,"given":"Xiaodong","family":"Gu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,27]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Li, F.F.: Dense-captioning events in videos. In: Proceedings of International Conference on Computer Vision, pp. 706\u2013715. IEEE, Venice (2017)","key":"11_CR1","DOI":"10.1109\/ICCV.2017.83"},{"doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C, Yang, Z., Nevatia, R.: TALL: temporal activity localization via language query. In: Proceedings of International Conference on Computer Vision, pp. 5267\u20135275. IEEE, Venice (2017)","key":"11_CR2","DOI":"10.1109\/ICCV.2017.563"},{"doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with temporal language. In: Proceedings of International Conference on Computer Vision, pp. 5803\u20135812. IEEE, Venice (2017)","key":"11_CR3","DOI":"10.1109\/ICCV.2017.618"},{"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 Winter Conference on Applications of Computer Vision, pp. 245\u2013253. IEEE, Waikoloa (2019)","key":"11_CR4","DOI":"10.1109\/WACV.2019.00032"},{"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 AAAI Conference on Artificial Intelligence. AAAI, New York (2020)","key":"11_CR5","DOI":"10.1609\/aaai.v34i07.6984"},{"doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Manohar, P.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497. IEEE, Boston (2015)","key":"11_CR6","DOI":"10.1109\/ICCV.2015.510"},{"doi-asserted-by":"crossref","unstructured":"Liu, M., Wang, X., Nie, L., He, X., Chen, B., Chua, T.: Attentive moment retrieval in videos. In: Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 15\u201324. ACM, Ann Arbor (2018)","key":"11_CR7","DOI":"10.1145\/3209978.3210003"},{"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 Computer Vision and Pattern Recognition, pp. 334\u2013343. IEEE, California (2019)","key":"11_CR8","DOI":"10.1109\/CVPR.2019.00042"},{"unstructured":"Hahn, M., Kadav, A., Rehg, J.M., Graf, H.P.: Tripping through time: efficient localization of activities in videos. arXiv preprint arXiv:1904.09936","key":"11_CR9"},{"doi-asserted-by":"crossref","unstructured":"Wang, J.W., Ma, L., Jiang, W.H.: Temporally grounding language queries in videos by contextual boundary-aware prediction. In: Proceedings of AAAI Conference on Artificial Intelligence. AAAI, New York (2020)","key":"11_CR10","DOI":"10.1609\/aaai.v34i07.6897"},{"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 Conference on Empirical Methods in Natural Language Processing, pp. 162\u2013171. ACL, Belgium (2018)","key":"11_CR11","DOI":"10.18653\/v1\/D18-1015"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Z., Lin, Z., Zhao, Z., Xiao, Z.: Cross-modal interaction networks for query-based moment retrieval in videos. In: Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 655-664. ACM, Paris (2019)","key":"11_CR12","DOI":"10.1145\/3331184.3331235"},{"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 Computer Vision and Pattern Recognition, pp. 1247\u20131257. IEEE, California (2019)","key":"11_CR13","DOI":"10.1109\/CVPR.2019.00134"},{"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 AAAI Conference on Artificial Intelligence, pp. 9062\u20139069 AAAI, Arlington (2019)","key":"11_CR14","DOI":"10.1609\/aaai.v33i01.33019062"},{"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 ACM International Conference on Multimedia, pp. 843\u2013851. ACM, Seoul (2018)","key":"11_CR15","DOI":"10.1145\/3240508.3240549"},{"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 AAAI Conference on Artificial Intelligence, pp. 9159\u20139166. AAAI, Arlington (2019)","key":"11_CR16","DOI":"10.1609\/aaai.v33i01.33019159"},{"doi-asserted-by":"crossref","unstructured":"Chen, S., Jiang, Y.G.: Semantic proposal for activity localization in videos via sentence query. In: Proceedings of AAAI Conference on Artificial Intelligence, pp. 8199\u20138206. AAAI, Arlington (2019)","key":"11_CR17","DOI":"10.1609\/aaai.v33i01.33018199"}],"container-title":["Lecture Notes in Computer Science","Advances in Neural Networks \u2013 ISNN 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-64221-1_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,28]],"date-time":"2020-11-28T11:08:38Z","timestamp":1606561718000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-64221-1_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030642204","9783030642211"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-64221-1_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"27 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISNN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cairo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Egypt","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2020","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":"isnn2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conference.cs.cityu.edu.hk\/isnn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"39","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":"24","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":"62% - 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":"3","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)"}}]}}