{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T19:48:20Z","timestamp":1775072900606,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2017YFB1300205"],"award-info":[{"award-number":["2017YFB1300205"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61573222"],"award-info":[{"award-number":["61573222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Research Program of Shandong Province","award":["2018CXGC1503"],"award-info":[{"award-number":["2018CXGC1503"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2020,12,1]]},"DOI":"10.1109\/tpami.2019.2920899","type":"journal-article","created":{"date-parts":[[2019,6,5]],"date-time":"2019-06-05T20:08:41Z","timestamp":1559765321000},"page":"3088-3101","source":"Crossref","is-referenced-by-count":65,"title":["Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5556-3896","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Bairui","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7331-6132","authenticated-orcid":false,"given":"Lin","family":"Ma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3865-8145","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref70","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref33","first-page":"3097","article-title":"Neural machine translation with reconstruction","author":"tu","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2718188"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref36","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"0","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.296"},{"key":"ref34","first-page":"820","article-title":"Dual learning for machine translation","author":"he","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref61","article-title":"Microsoft COCO captions: Data collection and evaluation server","volume":"abs 1504 325","author":"chen","year":"2015","journal-title":"CoRR"},{"key":"ref63","article-title":"ADADELTA: An adaptive learning rate method","volume":"abs 1212 5701","author":"zeiler","year":"2012","journal-title":"CoRR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref64","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref65","article-title":"Msr-vtt: A large video description dataset for bridging video and language [supplementary material]","author":"xu","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984062"},{"key":"ref29","first-page":"4197","article-title":"Video captioning with listwise supervision","author":"liu","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref67","article-title":"Delving deeper into convolutional networks for learning video representations","author":"ballas","year":"0","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2487976"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00834"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984065"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984066"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref59","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"2004","journal-title":"Proc ACL Workshop Text Summarization Branches Out"},{"key":"ref58","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume":"29","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref57","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":"ref56","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume":"1","author":"chen","year":"2011","journal-title":"Proc Proc 49th Annu Meeting Assoc Comput Linguist Human Lang Technol"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the Dimensionality of Data with Neural Networks","volume":"313","author":"hinton","year":"2006","journal-title":"Sci"},{"key":"ref54","article-title":"Reinforcement learning neural turing machines","volume":"abs 1505 521","author":"zaremba","year":"2015","journal-title":"CoRR"},{"key":"ref53","article-title":"Neural machine translation by jointly learning to align and translate","volume":"abs 1409 473","author":"bahdanau","year":"2014","journal-title":"CoRR"},{"key":"ref52","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11231","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc AAAI"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref12","first-page":"6959","article-title":"Learning to guide decoding for image captioning","author":"jiang","year":"2018","journal-title":"Proc AAAI"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref14","first-page":"2346","article-title":"Jointly modeling deep video and compositional text to bridge vision and language in a unified framework","author":"xu","year":"2015","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.03.021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2016.39"},{"key":"ref6","article-title":"Learning to answer questions from image using convolutional neural network","volume":"3","author":"ma","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699960"},{"key":"ref8","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume":"2","author":"karpathy","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2818048.2820013"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref45","article-title":"C3D: Generic features for video analysis","volume":"abs 1412 767","author":"tran","year":"2014","journal-title":"CoRR"},{"key":"ref48","first-page":"3789","article-title":"Dual supervised learning","author":"xia","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1103"},{"key":"ref42","first-page":"2924","article-title":"Automatic video description generation via lstm with joint two-stream encoding","author":"zhang","year":"2016","journal-title":"Proc 23rd Int Conf Pattern Recog"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9247540\/08731706.pdf?arnumber=8731706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T16:49:24Z","timestamp":1663606164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8731706\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,1]]},"references-count":70,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2920899","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,1]]}}}