{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T15:49:56Z","timestamp":1763308196722,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031446986"},{"type":"electronic","value":"9783031446993"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44699-3_18","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T08:02:39Z","timestamp":1696665759000},"page":"199-210","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Unified Framework for\u00a0Optimizing Video Corpus Retrieval and\u00a0Temporal Answer Grounding: Fine-Grained Modality Alignment and\u00a0Local-Global Optimization"],"prefix":"10.1007","author":[{"given":"Shuang","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zineng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyong","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,8]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Li, B., Weng, Y., Sun, B., Li, S.: Learning to locate visual answer in video corpus using question. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096391"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Weng, Y., Li, B.: Visual answer localization with cross-modal mutual knowledge transfer. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10095026"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., et al.: Understanding stories in movies through question-answering. In: CVPR pp. 4631\u20134640 (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Na, S., Lee, S., Kim, J., Kim, G.: A read-write memory network for movie story understanding. In: ICCV, pp. 677\u2013685. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.80"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Kim, J., Ma, M., Kim, K., Kim, S., Yoo, C.D.: Progressive attention memory network for movie story question answering. In: CVPR, pp. 8337\u20138346 (2019)","DOI":"10.1109\/CVPR.2019.00853"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Jang, Y., Song, Y., Yu, Y., Kim, Y., Kim, G.: Tgif-qa: toward spatio-temporal reasoning in visual question answering. In: CVPR, pp. 2758\u20132766 (2017)","DOI":"10.1109\/CVPR.2017.149"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Lei, J., Licheng, Y., Bansal, M., Berg, T.L.: Localized, compositional video question answering. In: EMNLP, Tvqa (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Berg, T.L., Bansal, M.: Tvqa+: spatio-temporal grounding for video question answering. In: ACL (2020)","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Kim, H., Tang, Z., Bansal, M.: Dense-caption matching and frame-selection gating for temporal localization in videoqa. In: ACL (2020)","DOI":"10.18653\/v1\/2020.acl-main.435"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Kim, J., Ma, M., Pham, T.X., Kim, K., Yoo, C.D.: Modality shifting attention network for multi-modal video question answering. In CVPR. IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.01012"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: Tall: temporal activity localization via language query. In: ICCV, pp. 5267\u20135275 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.C.: Localizing moments in video with natural language. In: ICCV, pp. 5804\u20135813. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"18_CR13","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, pp. 9159\u20139166. AAAI Press (2019)","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"18_CR14","unstructured":"Ma, Z., Ye, J., Yang, X., Liu, J.: Hcld: a hierarchical framework for zero-shot cross-lingual dialogue system. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 4492\u20134498 (2022)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., et al.: Weakly-supervised alignment of video with text. In: ICCV, pp. 4462\u20134470. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.507"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Mithun, N.C., Paul, S., Roy-Chowdhury, A.K.: Weakly supervised video moment retrieval from text queries. In: CVPR, pp. 11592\u201311601. Computer Vision Foundation\/IEEE (2019)","DOI":"10.1109\/CVPR.2019.01186"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Liu, J., Cheng, S., Zhou, Z., Gu, Y., Ye, J., Luo, H.: Enhancing multilingual document-grounded dialogue using cascaded prompt-based post-training models. In: Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, Toronto, Canada, pp. 44\u201351. Association for Computational Linguistics (July 2023)","DOI":"10.18653\/v1\/2023.dialdoc-1.5"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Ma, Z., Liu, Z., Ye, J.:. Sldt: sequential latent document transformer for multilingual document-based dialogue. In: Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pp. 57\u201367 (2023)","DOI":"10.18653\/v1\/2023.dialdoc-1.7"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Lin, Z., Zhao, Z., Zhang, Z., Wang, Q., Liu, H.: Weakly-supervised video moment retrieval via semantic completion network. In: AAAI, pp. 11539\u201311546. AAAI Press (2020)","DOI":"10.1609\/aaai.v34i07.6820"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"18_CR21","unstructured":"Zhang, J., et al.: Fengshenbang 1.0: Being the foundation of chinese cognitive intelligence. CoRR, abs\/ arXiv: 2209.02970 (2022)"},{"key":"18_CR22","unstructured":"Cui, Y., et al.: Pre-training with whole word masking for chinese bert. arXiv preprint arXiv:1906.08101 (2019)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Guo, L., He, X., Shao, S., Yuan, Z., Liu, J.: Mamo: masked multimodal modeling for fine-grained vision-language representation learning. arXiv preprint arXiv:2210.04183 (2022)","DOI":"10.1145\/3539618.3591721"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44699-3_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T06:06:10Z","timestamp":1698473170000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44699-3_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031446986","9783031446993"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44699-3_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Foshan","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":"12 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2023\/index.php","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":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"478","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":"143","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":"30% - 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":"4","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)"}}]}}