{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T02:25:21Z","timestamp":1783391121878,"version":"3.54.6"},"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1601101"],"award-info":[{"award-number":["2018YFB1601101"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1601100"],"award-info":[{"award-number":["2018YFB1601100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3067607","type":"journal-article","created":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T20:22:09Z","timestamp":1616444529000},"page":"69700-69709","source":"Crossref","is-referenced-by-count":27,"title":["Multi-Gate Attention Network for Image Captioning"],"prefix":"10.1109","volume":"9","author":[{"given":"Weitao","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4753-8022","authenticated-orcid":false,"given":"Xiying","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4884-323X","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6071-4481","authenticated-orcid":false,"given":"Qiang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bohong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correalation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref38","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","article-title":"On layer normalization in the transformer architecture","author":"xiong","year":"2020","journal-title":"arXiv 2002 04745"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref40","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc Workshop Text Summarization Branches Out"},{"key":"ref11","first-page":"10327","article-title":"Normalized and geometry-aware self-attention network for image captioning","author":"guo","year":"2020","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref12","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref17","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"2012","journal-title":"Proc 13th Conf Eur Chapter Assoc Comput Linguistics"},{"key":"ref18","first-page":"359","article-title":"Collective generation of natural image descriptions","volume":"1","author":"kuznetsova","year":"2012","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref19","first-page":"606","article-title":"Choosing linguistics over vision to describe images","author":"gupta","year":"2012","journal-title":"Proc 26th AAAI Conf Artif Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2944970"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/rs9080790"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref8","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00188"},{"key":"ref45","first-page":"211","article-title":"Comprehensive image captioning via scene graph decomposition","author":"zhong","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref22","first-page":"3981","article-title":"Reference based LSTM for image captioning","author":"chen","year":"2017","journal-title":"Proc AAAI"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413753"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.664"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6290"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107448"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09382255.pdf?arnumber=9382255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:13Z","timestamp":1639770913000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9382255\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3067607","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}