{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:12:21Z","timestamp":1766067141308,"version":"3.37.3"},"reference-count":45,"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":["61976159"],"award-info":[{"award-number":["61976159"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["2018AAA0101303"],"award-info":[{"award-number":["2018AAA0101303"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing","award":["17DZ2251600"],"award-info":[{"award-number":["17DZ2251600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.2990074","type":"journal-article","created":{"date-parts":[[2020,4,23]],"date-time":"2020-04-23T19:58:36Z","timestamp":1587671916000},"page":"835-845","source":"Crossref","is-referenced-by-count":45,"title":["CaptionNet: A Tailor-made Recurrent Neural Network for Generating Image Descriptions"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7644-2073","authenticated-orcid":false,"given":"Longyu","family":"Yang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-4871","authenticated-orcid":false,"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Pengjie","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Qinyu","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref38","article-title":"Very deep convolutional networks for large-scale image recognition","author":"karen","year":"0","journal-title":"Proc ICLR’15"},{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc ICLR’15"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref36","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"0","journal-title":"Proc ICLR’15"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc ECCV’14"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref7","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc ICML’15"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751140"},{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc ICLR’15"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref42","first-page":"6837","article-title":"Stack-captioning: Coarse-to-fine learning for image captioning","author":"gu","year":"0","journal-title":"Proc AAAI’18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240632"},{"key":"ref26","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Proc NIPS’00"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref25","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"0","journal-title":"Proc ICLR’16"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09076851.pdf?arnumber=9076851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:37Z","timestamp":1652194297000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9076851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.2990074","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2021]]}}}