{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:28:23Z","timestamp":1781087303873,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research and Development Program of China in the 14th Five-Year","award":["2021YFF0602103, and 2021YFF0602102"],"award-info":[{"award-number":["2021YFF0602103, and 2021YFF0602102"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,25]]},"DOI":"10.1145\/3704323.3704388","type":"proceedings-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T08:25:22Z","timestamp":1736238322000},"page":"407-411","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["NewsCap: Audio-guided Context-aware Network for News Video Captioning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6133-3842","authenticated-orcid":false,"given":"Zijian","family":"Zeng","sequence":"first","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Beijing, China and Department of Electronic Engineering,Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3884-5896","authenticated-orcid":false,"given":"Yue","family":"Zheng","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Beijing, China and Department of Electronic Engineering,Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6629-7228","authenticated-orcid":false,"given":"Yali","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Beijing, China and Department of Electronic Engineering,Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7809-1932","authenticated-orcid":false,"given":"Shengjin","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Beijing, China and Department of Electronic Engineering,Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,1,7]]},"reference":[{"key":"e_1_3_3_1_2_2","first-page":"65","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65\u201372."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002497"},{"key":"e_1_3_3_1_4_2","unstructured":"Xinlei Chen Hao Fang Tsung-Yi Lin Ramakrishna Vedantam Saurabh Gupta Piotr Doll\u00e1r and C\u00a0Lawrence Zitnick. 2015. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1504.00325 (2015)."},{"key":"e_1_3_3_1_5_2","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.04805 (2018)."},{"key":"e_1_3_3_1_6_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et\u00a0al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020)."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"e_1_3_3_1_8_2","first-page":"74","volume-title":"Text summarization branches out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74\u201381."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"e_1_3_3_1_10_2","unstructured":"Huaishao Luo Lei Ji Ming Zhong Yang Chen Wen Lei Nan Duan and Tianrui Li. 2021. Clip4clip: An empirical study of clip for end to end video clip retrieval. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.08860 (2021)."},{"key":"e_1_3_3_1_11_2","first-page":"311","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311\u2013318."},{"key":"e_1_3_3_1_12_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688196"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"}],"event":{"name":"ICCPR 2024: 2024 13th International Conference on Computing and Pattern Recognition","location":"Tianjin China","acronym":"ICCPR 2024"},"container-title":["Proceedings of the 2024 13th International Conference on Computing and Pattern Recognition"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3704323.3704388","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3704323.3704388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:05Z","timestamp":1750295885000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3704323.3704388"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"references-count":19,"alternative-id":["10.1145\/3704323.3704388","10.1145\/3704323"],"URL":"https:\/\/doi.org\/10.1145\/3704323.3704388","relation":{},"subject":[],"published":{"date-parts":[[2024,10,25]]},"assertion":[{"value":"2025-01-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}