{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T05:57:15Z","timestamp":1743055035128,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819996391"},{"type":"electronic","value":"9789819996407"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-981-99-9640-7_19","type":"book-chapter","created":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T15:02:38Z","timestamp":1704380558000},"page":"265-275","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CMGN: Cross-Modal Grounding Network for\u00a0Temporal Sentence Retrieval in\u00a0Video"],"prefix":"10.1007","author":[{"given":"Qun","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bolin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,5]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: TALL: temporal activity localization via language query. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5277\u20135285 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"19_CR2","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: IEEE International Conference on Computer Vision, pp. 5803\u20135812 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"issue":"8","key":"19_CR3","first-page":"4065","volume":"44","author":"J Dong","year":"2021","unstructured":"Dong, J., et al.: Dual encoding for video retrieval by text. IEEE Trans. Pattern Anal. Mach. Intell. 44(8), 4065\u20134080 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Liu, M., Wang, X., Nie, L., et al.: Attentive moment retrieval in videos. In: 41nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 15\u201324 (2018)","DOI":"10.1145\/3209978.3210003"},{"key":"19_CR5","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: 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 655\u2013664 (2019)","DOI":"10.1145\/3331184.3331235"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Chen, X., Ma, L., Jie, Z., Chua, T.S.: Temporally grounding natural sentence in video. In: 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 162\u2013171 (2018)","DOI":"10.18653\/v1\/D18-1015"},{"key":"19_CR7","unstructured":"Yuan, Y., Ma, L., Wang, J., Liu, W., Zhu, W.: Semantic conditioned dynamic modulation for temporal sentence grounding in videos. In: Advances in Neural Information Processing Systems (NIPS), pp. 534\u2013544 (2019)"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Wang, J., Ma, L., Jiang, W.: Temporally grounding language queries in videos by contextual boundary-aware prediction. In: AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 12168\u201312175 (2020)","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"19_CR9","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1247\u20131257 (2019)","DOI":"10.1109\/CVPR.2019.00134"},{"key":"19_CR10","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: AAAI Conference on Artificial Intelligence, vol. 34, no. 07 (2020)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"19_CR11","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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7026\u20137035 (2021)","DOI":"10.1109\/CVPR46437.2021.00695"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Liu, D., Qu, X., Liu, X. Y., Dong, J., Zhou, P., Xu, Z.: Jointly cross- and self- modal graph attention network for query-based moment localization. In: 28th ACM International Conference on Multimedia, pp. 4070\u20134078 (2020)","DOI":"10.1145\/3394171.3414026"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Soldan, M., Xu, M., Qu, S., Tegner, J., Ghanem, B.: VLG-net: video-language graph matching network for video grounding. In: 2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 3217\u20133227 (2020)","DOI":"10.1109\/ICCVW54120.2021.00361"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, B., Jiang, B., Yang, C., Pang, L.: Dual-channel localization networks for moment retrieval with natural language. In: International Conference on Multimedia Retrieval (ICMR), pp. 351\u2013359 (2022)","DOI":"10.1145\/3512527.3531394"},{"key":"19_CR17","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":"19_CR18","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":"19_CR19","doi-asserted-by":"crossref","unstructured":"Xiao, S., Chen, L., Zhang, S., Ji, W., Shao, J., Ye, L., Xiao, J.: Boundary proposal network for two-stage natural language video localization. In: AAAI Conference on Artificial Intelligence, vol. 35, no. 04, pp. 2986\u20132994 (2021)","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"19_CR20","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, no. 01, pp. 9062\u20139069 (2019)","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, H., Sun, A., Jing, W., Zhou, J.T.: Span-based localizing network for natural language video localization. In: The 58th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 6543\u20136554 (2020)","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Gao, J., Xu, C.: Fast video moment retrieval. In: IEEE\/CVF International Conference on Computer Vision, pp. 1523\u20131532 (2021)","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"19_CR23","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, vol. 35, no. 03, pp. 1902\u20131910 (2021)","DOI":"10.1609\/aaai.v35i3.16285"},{"key":"19_CR24","unstructured":"Chung, J., Gulcehre, C., Cho, K., et al.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"}],"container-title":["Communications in Computer and Information Science","Computer Supported Cooperative Work and Social Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-9640-7_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T15:16:59Z","timestamp":1704381419000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-9640-7_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819996391","9789819996407"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-9640-7_19","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"5 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ChineseCSCW","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF Conference on Computer Supported Cooperative Work  and Social Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Harbin","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":"18 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"chinesecscw2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conf.scholat.com\/ccscw\/2023","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":"Yes. 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":"221","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":"54","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":"28","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":"24% - 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":"5","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)"}}]}}