{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T01:16:25Z","timestamp":1778634985098,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation for Distinguished Young Scholars of China","award":["T2325018"],"award-info":[{"award-number":["T2325018"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171274"],"award-info":[{"award-number":["62171274"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272036"],"award-info":[{"award-number":["62272036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2241228"],"award-info":[{"award-number":["U2241228"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tiv.2024.3353172","type":"journal-article","created":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T18:27:45Z","timestamp":1705429665000},"page":"4373-4382","source":"Crossref","is-referenced-by-count":1,"title":["Anticipation Video Captioning of Aerial Refueling Based on Combined Attention Masking Mechanism"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7713-1808","authenticated-orcid":false,"given":"Shuai","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8558-1822","authenticated-orcid":false,"given":"Wei","family":"Tong","sequence":"additional","affiliation":[{"name":"College of Automation and College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7274-390X","authenticated-orcid":false,"given":"Ya","family":"Duan","sequence":"additional","affiliation":[{"name":"Flight Test Technology and Engineering Center, Chinese Flight Test Establishment, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6473-9272","authenticated-orcid":false,"given":"Weidong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1467-1776","authenticated-orcid":false,"given":"Guangyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Beijing Research Center of Urban Traffic Information Sensing and Service Technologies, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1301-9870","authenticated-orcid":false,"given":"Edmond Q.","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3223131"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3274536"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123486"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123552"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123555"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00102"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3070140"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2021.3098733"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2957992"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9512"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3158546"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123033"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3164507"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2023.111051"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3256799"},{"key":"ref20","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Hafner","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.319"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00102"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00354"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.326"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00351"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.706"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103230"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_36"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.77"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref34","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Chen","year":"2011"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref36","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref41","first-page":"1079","article-title":"Delving deeper into the decoder for video captioning","volume-title":"Proc. ECAI 24th Eur. Conf. Artif. Intell., Including 10th Conf. Prestigious Appl. Artif. Intell.","author":"Chen","year":"2020"},{"key":"ref42","article-title":"Univilm: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274857\/10517859\/10400850.pdf?arnumber=10400850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T17:47:38Z","timestamp":1751046458000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10400850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":43,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2024.3353172","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}