{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:40:58Z","timestamp":1777128058396,"version":"3.51.4"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2021RC216"],"award-info":[{"award-number":["2021RC216"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62006015"],"award-info":[{"award-number":["62006015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61672089"],"award-info":[{"award-number":["61672089"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61971446"],"award-info":[{"award-number":["61971446"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61572064"],"award-info":[{"award-number":["61572064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61906013"],"award-info":[{"award-number":["61906013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CEFLA Audio-Video Restoration and Evaluation Key Laboratory of Ministry of Culture and Tourism"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1109\/tcsvt.2022.3165934","type":"journal-article","created":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T19:30:15Z","timestamp":1649446215000},"page":"6293-6307","source":"Crossref","is-referenced-by-count":30,"title":["Bridging Video and Text: A Two-Step Polishing Transformer for Video Captioning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2206-5051","authenticated-orcid":false,"given":"Wanru","family":"Xu","sequence":"first","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenjiang","family":"Miao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6054-7970","authenticated-orcid":false,"given":"Yi","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9520-5425","authenticated-orcid":false,"given":"Lili","family":"Wan","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4302-2889","authenticated-orcid":false,"given":"Qiang","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2940007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00714"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988435"},{"key":"ref6","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/88"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978942"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2942030"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018271"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2894139"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063423"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867286"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475519"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref20","article-title":"Reconstruct and represent video contents for captioning via reinforcement learning","author":"Zhang","year":"2019","journal-title":"arXiv:1906.01452"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2936526"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014606"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00693"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12330"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.475767"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951226"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00486"},{"key":"ref33","article-title":"Look and modify: Modification networks for image captioning","author":"Sammani","year":"2019","journal-title":"arXiv:1909.03169"},{"key":"ref34","first-page":"10073","article-title":"A retrieve-and-edit framework for predicting structured outputs","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Hashimoto"},{"key":"ref35","first-page":"82","article-title":"Think and tell: Preview network for image captioning","volume-title":"Proc. BMVC","author":"Zhu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16421"},{"issue":"8","key":"ref38","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065823"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00042"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107702"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2956593"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref45","first-page":"847","article-title":"TVT: Two-view transformer network for video captioning","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Chen"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.24"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16301"},{"key":"ref48","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Hum. Lang. Technol.","volume":"1","author":"Chen"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"issue":"1","key":"ref53","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref55","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref56","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"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref58","article-title":"Transparent human evaluation for image captioning","author":"Kasai","year":"2021","journal-title":"arXiv:2111.08940"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9875133\/09751606.pdf?arnumber=9751606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T00:25:34Z","timestamp":1705537534000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9751606\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":58,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3165934","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9]]}}}