{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:08:24Z","timestamp":1755907704683,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T00:00:00Z","timestamp":1698364800000},"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"],"award-info":[{"award-number":["2021YFF0602103"]}]},{"name":"National Key Research and Development Program of China in the 14th Five-Year","award":["2021YFF0602102"],"award-info":[{"award-number":["2021YFF0602102"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,27]]},"DOI":"10.1145\/3633637.3633643","type":"proceedings-article","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T08:08:05Z","timestamp":1709107685000},"page":"40-44","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FTAN: Exploring Frame-Text Attention for lightweight 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, China and Department of Electronic Engineering,Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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, China and Department of Electronic Engineering,Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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, China and Department of Electronic Engineering,Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2230-9879","authenticated-orcid":false,"given":"Siqi","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, China and Department of Electronic Engineering,Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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, China and Department of Electronic Engineering,Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,2,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002497"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Xuelong Li Bin Zhao Xiaoqiang Lu 2017. Mam-rnn: multi-level attention model based rnn for video captioning.. In IJCAI Vol.\u00a02017. 2208\u20132214.","DOI":"10.24963\/ijcai.2017\/307"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"e_1_3_2_1_12_1","volume-title":"Hierarchical LSTM with adjusted temporal attention for video captioning. arXiv preprint arXiv:1706.01231","author":"Song Jingkuan","year":"2017","unstructured":"Jingkuan Song, Zhao Guo, Lianli Gao, Wu Liu, Dongxiang Zhang, and Heng\u00a0Tao Shen. 2017. Hierarchical LSTM with adjusted temporal attention for video captioning. arXiv preprint arXiv:1706.01231 (2017)."},{"key":"e_1_3_2_1_13_1","volume-title":"Sequence to sequence learning with neural networks. Advances in neural information processing systems 27","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc\u00a0V Le. 2014. Sequence to sequence learning with neural networks. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_14_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_15_1","volume-title":"Translating videos to natural language using deep recurrent neural networks. arXiv preprint arXiv:1412.4729","author":"Venugopalan Subhashini","year":"2014","unstructured":"Subhashini Venugopalan, Huijuan Xu, Jeff Donahue, Marcus Rohrbach, Raymond Mooney, and Kate Saenko. 2014. Translating videos to natural language using deep recurrent neural networks. arXiv preprint arXiv:1412.4729 (2014)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"}],"event":{"name":"ICCPR 2023: 2023 12th International Conference on Computing and Pattern Recognition","acronym":"ICCPR 2023","location":"Qingdao China"},"container-title":["2023 12th International Conference on Computing and Pattern Recognition"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3633637.3633643","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3633637.3633643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:19:15Z","timestamp":1755883155000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3633637.3633643"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,27]]},"references-count":24,"alternative-id":["10.1145\/3633637.3633643","10.1145\/3633637"],"URL":"https:\/\/doi.org\/10.1145\/3633637.3633643","relation":{},"subject":[],"published":{"date-parts":[[2023,10,27]]},"assertion":[{"value":"2024-02-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}