{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T02:03:44Z","timestamp":1769047424862,"version":"3.49.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":["61922086"],"award-info":[{"award-number":["61922086"]}],"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":["61872366"],"award-info":[{"award-number":["61872366"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1109\/tmm.2019.2951226","type":"journal-article","created":{"date-parts":[[2019,11,4]],"date-time":"2019-11-04T20:26:24Z","timestamp":1572899184000},"page":"2149-2162","source":"Crossref","is-referenced-by-count":41,"title":["Show, Tell, and Polish: Ruminant Decoding for Image Captioning"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4340-4000","authenticated-orcid":false,"given":"Longteng","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0903-9131","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shichen","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanqing","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref37","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"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","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"0","journal-title":"Proc Neural Inf Process Syst Conf"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref29","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref2","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_21"},{"key":"ref26","first-page":"6837","article-title":"Stack-captioning: Coarse-to-fine learning for image captioning","author":"gu","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref25","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"0","journal-title":"Proc Neural Inf Process Syst Conf"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126717"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240632"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1019"},{"key":"ref52","first-page":"957","article-title":"From word embeddings to document distances","author":"kusner","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref40","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc of the Meeting of the Assoc for Computational Linguistics"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"0","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.138"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751140"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref6","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Neural Inf Process Syst Conf"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref8","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Neural Inf Process Syst Conf"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref9","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref48","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"0","journal-title":"Proc of Workshop on Text Summarization Branches Out"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref41","article-title":"Actor-critic sequence training for image captioning","author":"zhang","year":"0","journal-title":"Proc NIPS Workshop Vis -Grounded Interact Lang"},{"key":"ref44","first-page":"308","volume":"2","author":"barrault","year":"0","journal-title":"Proc 3rd Conf Mach Translation"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6452"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9146956\/08890876.pdf?arnumber=8890876","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:55:44Z","timestamp":1651074944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8890876\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":56,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2951226","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8]]}}}