{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T15:50:06Z","timestamp":1763308206759,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"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_20","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T08:02:39Z","timestamp":1696665759000},"page":"221-232","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Improving Cross-Modal Visual Answer Localization in\u00a0Chinese Medical Instructional Video Using Language Prompts"],"prefix":"10.1007","author":[{"given":"Zineng","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Cheng","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"}]},{"given":"Jian","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,8]]},"reference":[{"key":"20_CR1","unstructured":"Zhang, H., Sun, A., Jing, W., Zhou, J.T.: Temporal sentence grounding in videos: a survey and future directions. arXiv preprint arXiv:2201.08071 (2022)"},{"key":"20_CR2","doi-asserted-by":"publisher","first-page":"1338","DOI":"10.1109\/TMM.2021.3063631","volume":"24","author":"H Tang","year":"2021","unstructured":"Tang, H., Zhu, J., Liu, M., Gao, Z., Cheng, Z.: Frame-wise cross-modal matching for video moment retrieval. IEEE Trans. Multimedia 24, 1338\u20131349 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.L.: TVQA: localized, compositional video question answering. arXiv preprint arXiv:1809.01696 (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Li, B., Weng, Y., Sun, B., Li, S.: Towards visual-prompt temporal answering grounding in medical instructional video. arXiv preprint arXiv:2203.06667 (2022)","DOI":"10.36227\/techrxiv.22182736.v1"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Weng, Y., Li, B.: Visual answer localization with cross-modal mutual knowledge transfer. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095026"},{"key":"20_CR6","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 5803\u20135812 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, H., Sun, A., Jing, W., Zhou, J.T.: Span-based localizing network for natural language video localization. arXiv preprint arXiv:2004.13931 (2020)","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"20_CR8","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 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096391"},{"key":"20_CR9","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training (2018)"},{"issue":"8","key":"20_CR10","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Jeffrey, W., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"20_CR11","unstructured":"Petroni, F., et al.: Language models as knowledge bases? arXiv preprint arXiv:1909.01066 (2019)"},{"key":"20_CR12","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1162\/tacl_a_00342","volume":"8","author":"A Talmor","year":"2020","unstructured":"Talmor, A., Elazar, Y., Goldberg, Y., Berant, J.: oLMpics-on what language model pre-training captures. Trans. Assoc. Comput. Linguist. 8, 743\u2013758 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"20_CR13","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 (2023)","DOI":"10.18653\/v1\/2023.dialdoc-1.5"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Schick, T., Sch\u00fctze, H.: Exploiting cloze questions for few shot text classification and natural language inference. arXiv preprint arXiv:2001.07676 (2020)","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: mPLUG: effective and efficient vision-language learning by cross-modal skip-connections. arXiv preprint arXiv:2205.12005 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"20_CR16","unstructured":"Zhang, J., et al.: Fengshenbang 1.0: being the foundation of Chinese cognitive intelligence. CoRR, abs\/2209.02970 (2022)"},{"key":"20_CR17","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":"20_CR18","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"issue":"1","key":"20_CR20","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41597-023-02036-y","volume":"10","author":"D Gupta","year":"2023","unstructured":"Gupta, D., Attal, K., Demner-Fushman, D.: A dataset for medical instructional video classification and question answering. Sci. Data 10(1), 158 (2023)","journal-title":"Sci. Data"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Cui, Y., Che, W., Liu, T., Qin, B., Wang, S., Hu, G.: Revisiting pre-trained models for Chinese natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, pp. 657\u2013668. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"key":"20_CR22","unstructured":"Cui, Y., Che, W., Liu, T., Qin, B., Yang, Z.: Pre-training with whole word masking for Chinese BERT. arXiv preprint arXiv:1906.08101 (2019)"}],"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_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T06:06:00Z","timestamp":1698473160000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44699-3_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031446986","9783031446993"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44699-3_20","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)"}}]}}