{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T10:35:02Z","timestamp":1742985302703,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819988495"},{"type":"electronic","value":"9789819988501"}],"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\/978-981-99-8850-1_25","type":"book-chapter","created":{"date-parts":[[2024,2,3]],"date-time":"2024-02-03T18:02:05Z","timestamp":1706983325000},"page":"305-316","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PointerNet with Local and Global Contexts for Natural Language Moment Localization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7375-452X","authenticated-orcid":false,"given":"Linwei","family":"Ye","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8428-1131","authenticated-orcid":false,"given":"Zhi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9447-1791","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,4]]},"reference":[{"key":"25_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: IEEE International Conference on Computer Vision, pp. 5803\u20135812 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"25_CR3","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, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Conference on Empirical Methods in Natural Language Processing (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: TALL: temporal activity localization via language query. In: IEEE International Conference on Computer Vision, pp. 5267\u20135275 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Niebles, J.C.: Dense-captioning events in videos. In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Liu, C., Lin, Z., Shen, X., Yang, J., Lu, X., Yuille, A.L.: Recurrent multimodal interaction for referring image segmentation. In: IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Liu, M., Wang, X., Nie, L., He, X., Chen, B., Chua, T.S.: Attentive moment retrieval in videos. In: ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 15\u201324 (2018)","DOI":"10.1145\/3209978.3210003"},{"key":"25_CR9","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: ACM International Conference on Multimedia, pp. 843\u2013851 (2018)","DOI":"10.1145\/3240508.3240549"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Ma, S., Sigal, L., Sclaroff, S.: Learning activity progression in LSTMs for activity detection and early detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1942\u20131950 (2016)","DOI":"10.1109\/CVPR.2016.214"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Conference on Empirical Methods in Natural Language Processing, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"25_CR12","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."},{"issue":"3","key":"25_CR13","first-page":"1","volume":"4","author":"M Tunguturi","year":"2022","unstructured":"Tunguturi, M.: Moment localization using multi-scale 2D temporal adjacent networks and natural language. Int. J. Mach. Learn. Sustain. Dev. 4(3), 1\u201310 (2022)","journal-title":"Int. J. Mach. Learn. Sustain. Dev."},{"issue":"1","key":"25_CR14","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1080\/02724980343000189","volume":"57","author":"G Underwood","year":"2004","unstructured":"Underwood, G., Jebbett, L., Roberts, K.: Inspecting pictures for information to verify a sentence: Eye movements in general encoding and in focused search. Q. J. Exp. Psychol. Sect. A 57(1), 165\u2013182 (2004)","journal-title":"Q. J. Exp. Psychol. Sect. A"},{"key":"25_CR15","unstructured":"Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Advances in Neural Information Processing Systems, pp. 2692\u20132700 (2015)"},{"key":"25_CR16","unstructured":"Wang, W., Huang, Y., Wang, L.: Language-driven temporal activity localization: a semantic matching reinforcement learning model. In: IEEE Conference on Computer Vision and Pattern Recognition,"},{"key":"25_CR17","unstructured":"Wei, Z., et al.: Sequence-to-segment networks for segment detection. In: Advances in Neural Information Processing Systems, pp. 3507\u20133516 (2018)"},{"key":"25_CR18","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. vol. 35, pp. 2986\u20132994 (2021)","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"25_CR19","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: AAAI Conference on Artificial Intelligence. vol. 33, pp. 9062\u20139069 (2019)","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"25_CR20","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: AAAI Conference on Artificial Intelligence. vol. 33, pp. 9159\u20139166 (2019)","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"25_CR21","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, pp. 1247\u20131257 (2019)","DOI":"10.1109\/CVPR.2019.00134"},{"issue":"8","key":"25_CR22","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":"25_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, L., Radke, R.J.: Natural language video moment localization through query-controlled temporal convolution. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 682\u2013690 (2022)","DOI":"10.1109\/WACV51458.2022.00258"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Zheng, M., Huang, Y., Chen, Q., Liu, Y.: Weakly supervised video moment localization with contrastive negative sample mining. In: AAAI Conference on Artificial Intelligence. vol. 36, pp. 3517\u20133525 (2022)","DOI":"10.1609\/aaai.v36i3.20263"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8850-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,3]],"date-time":"2024-02-03T18:05:49Z","timestamp":1706983549000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8850-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819988495","9789819988501"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8850-1_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"4 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fuzhou","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":"22 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"376","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":"101","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":"16","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":"27% - 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":"2.9","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":"1.9","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)"}}]}}