{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:40:51Z","timestamp":1777128051438,"version":"3.51.4"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61703436"],"award-info":[{"award-number":["61703436"]}],"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":["61572064"],"award-info":[{"award-number":["61572064"]}],"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":["61906013"],"award-info":[{"award-number":["61906013"]}],"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":["61273274"],"award-info":[{"award-number":["61273274"]}],"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":["61876016"],"award-info":[{"award-number":["61876016"]}],"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":["61632004"],"award-info":[{"award-number":["61632004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CELFA"},{"name":"National Key R&D Program of China","award":["2018AAA0100302"],"award-info":[{"award-number":["2018AAA0100302"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2019M650469"],"award-info":[{"award-number":["2019M650469"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3002669","type":"journal-article","created":{"date-parts":[[2020,6,15]],"date-time":"2020-06-15T22:11:15Z","timestamp":1592259075000},"page":"1772-1784","source":"Crossref","is-referenced-by-count":48,"title":["Deep Reinforcement Polishing Network for Video Captioning"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2206-5051","authenticated-orcid":false,"given":"Wanru","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenjiang","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9520-5425","authenticated-orcid":false,"given":"Lili","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6054-7970","authenticated-orcid":false,"given":"Yi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4302-2889","authenticated-orcid":false,"given":"Qiang","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951226"},{"key":"ref38","article-title":"Think and tell: Preview network for image captioning","author":"zhu","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref32","first-page":"3059","article-title":"Weakly supervised dense event captioning in videos","author":"duan","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref37","first-page":"1784","article-title":"Deliberation networks: Sequence generation beyond one-pass decoding","author":"xia","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00640"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00675"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00042"},{"key":"ref63","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.364"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855422"},{"key":"ref29","article-title":"Improving image captioning with conditional generative adversarial nets","author":"chen","year":"2018","journal-title":"arXiv 1805 07112"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref20","first-page":"1112","article-title":"Hierarchical LSTMs with adaptive attention for visual captioning","volume":"42","author":"gao","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018271"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/164"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1103"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00714"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref57","first-page":"6894","article-title":"Integrating both visual and audio cues for enhanced video caption","author":"hao","year":"2018","journal-title":"Proc 32th AAAI Conf Artif Intell"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00013"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.012"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref40","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","first-page":"358","article-title":"Less is more: Picking informative frames for video captioning","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33863-2_37"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref17","article-title":"Reconstruct and represent video contents for captioning via reinforcement learning","author":"zhang","year":"2019","journal-title":"arXiv 1906 01452"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3355390"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref6","first-page":"1218","article-title":"Integrating language and vision to generate natural language descriptions of videos in the wild","author":"thomason","year":"2014","journal-title":"Proc Int Conf Comput Linguist"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/877"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130425"},{"key":"ref49","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref7","article-title":"Video in sentences out","author":"barbu","year":"2012","journal-title":"arXiv 1204 2742"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref46","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref48","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc ACL Workshop Text Summarization Branches Out"},{"key":"ref47","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref42","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc Annu Meeting Assoc Comput Linguistics Human Lang Technol"},{"key":"ref41","first-page":"4278","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc 31th AAAI Conf Artif Intell"},{"key":"ref44","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc USENIX Symp Oper Syst Des Implement"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09117178.pdf?arnumber=9117178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:38Z","timestamp":1652194298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9117178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3002669","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}