{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:19:16Z","timestamp":1773137956632,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFE0210700"],"award-info":[{"award-number":["2023YFE0210700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62161013"],"award-info":[{"award-number":["62161013"]}],"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":["62441203"],"award-info":[{"award-number":["62441203"]}],"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":["62311530101"],"award-info":[{"award-number":["62311530101"]}],"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":["62132006"],"award-info":[{"award-number":["62132006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20242BAB23012"],"award-info":[{"award-number":["20242BAB23012"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022957","name":"Double Thousand Plan of Jiangxi Province","doi-asserted-by":"publisher","award":["jxsq2023101092"],"award-info":[{"award-number":["jxsq2023101092"]}],"id":[{"id":"10.13039\/100022957","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013064","name":"Key Research and Development Program of Jiangxi Province","doi-asserted-by":"publisher","award":["20252BCE310034"],"award-info":[{"award-number":["20252BCE310034"]}],"id":[{"id":"10.13039\/501100013064","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tcsvt.2025.3616201","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:39:41Z","timestamp":1759772381000},"page":"3185-3200","source":"Crossref","is-referenced-by-count":0,"title":["Text-Conditional Visual-Language Alignment for Video Captioning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4144-6725","authenticated-orcid":false,"given":"Wenhui","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Computing and Artificial Intelligence and Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing, Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3855-1244","authenticated-orcid":false,"given":"Wenbin","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence and Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing, Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haijun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence and Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing, Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1979-0571","authenticated-orcid":false,"given":"Zhizhen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence and Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing, Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6946-3586","authenticated-orcid":false,"given":"Yuming","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence and Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing, Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7658-3845","authenticated-orcid":false,"given":"Yuxin","family":"Peng","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Sany Heavy Industry Company Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9982-9887","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Sany Heavy Industry Company Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref2","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"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3295098"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3327677"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28032"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548237"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3541965"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3502736"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3277827"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3546828"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3158546"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3177318"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3232634"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/180"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01816"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3323491"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063423"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01925"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25484"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3322329"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01724"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16301"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7006"},{"key":"ref31","article-title":"Modeling uncertainty with hedged instance embedding","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Oh"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref33","article-title":"Smoothing the geometry of probabilistic box embeddings","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref35","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization ACL","author":"Lin"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref38","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01740"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.eval4nlp-1.4"},{"key":"ref43","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1220"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref50","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020","journal-title":"arXiv:2002.06353"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3192709"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01426"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01413"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref59","article-title":"Support-set bottlenecks for video-text representation learning","author":"Patrick","year":"2020","journal-title":"arXiv:2010.02824"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref61","article-title":"VALUE: A multi-task benchmark for video-and-language understanding evaluation","author":"Li","year":"2021","journal-title":"arXiv:2106.04632"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479216"},{"key":"ref63","article-title":"VideoCoCa: Video-text modeling with zero-shot transfer from contrastive captioners","author":"Yan","year":"2022","journal-title":"arXiv:2212.04979"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3479776"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413746"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_21"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00674"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/131"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746751"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02193"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02436"},{"key":"ref73","article-title":"MiniGPT4-video: Advancing multimodal LLMs for video understanding with interleaved visual-textual tokens","author":"Ataallah","year":"2024","journal-title":"arXiv:2404.03413"},{"key":"ref74","article-title":"AuroraCap: Efficient, performant video detailed captioning and a new benchmark","author":"Chai","year":"2024","journal-title":"arXiv:2410.03051"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11185188.pdf?arnumber=11185188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:01:11Z","timestamp":1773086471000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11185188\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":74,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3616201","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}