{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T09:07:57Z","timestamp":1777626477915,"version":"3.51.4"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572306"],"award-info":[{"award-number":["61572306"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2017YFB0701600"],"award-info":[{"award-number":["2017YFB0701600"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Committee of Shanghai Municipality","doi-asserted-by":"publisher","award":["19511121002"],"award-info":[{"award-number":["19511121002"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Engineering Research Center of Intelligent Computing System","award":["19DZ2252600"],"award-info":[{"award-number":["19DZ2252600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3024639","type":"journal-article","created":{"date-parts":[[2020,9,18]],"date-time":"2020-09-18T20:17:42Z","timestamp":1600460262000},"page":"213437-213446","source":"Crossref","is-referenced-by-count":8,"title":["A Sparse Transformer-Based Approach for Image Captioning"],"prefix":"10.1109","volume":"8","author":[{"given":"Zhou","family":"Lei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7215-3765","authenticated-orcid":false,"given":"Congcong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengbo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5068-512X","authenticated-orcid":false,"given":"Xianrui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","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":"ref38","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"2004","journal-title":"Proc Workshop Text Summarization Branches Out"},{"key":"ref33","article-title":"Augmenting self-attention with persistent memory","author":"sukhbaatar","year":"2019","journal-title":"arXiv 1907 01470"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00859"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00856"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref36","first-page":"376","article-title":"Meteor universal: Language specific translation evaluation for any target language","author":"lavie","year":"2014","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref35","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref28","first-page":"10971","article-title":"X-linear attention networks for image captioning","author":"pan","year":"2020","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/708"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00898"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref20","first-page":"8940","article-title":"Adaptively aligned image captioning via adaptive attention time","author":"huang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref21","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016","journal-title":"arXiv 1609 02907"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref25","first-page":"11135","article-title":"Image captioning: Transforming objects into words","author":"herdade","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2014","journal-title":"arXiv 1412 6632"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/110"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref11","article-title":"Generating long sequences with sparse transformers","author":"child","year":"2019","journal-title":"arXiv 1904 10509"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref12","article-title":"Explicit sparse transformer: Concentrated attention through explicit selection","author":"zhao","year":"2019","journal-title":"arXiv 1912 11637"},{"key":"ref13","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"arXiv 1405 0312"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01278"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref6","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"arXiv 1706 03762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref46","first-page":"1","article-title":"Stack-captioning: Coarse-to-fine learning for image captioning","author":"gu","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref48","first-page":"2422","article-title":"Mind’s eye: A recurrent visual representation for image caption generation","author":"chen","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240632"},{"key":"ref42","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref44","article-title":"Boosting image captioning with attributes","author":"yao","year":"2016","journal-title":"arXiv 1611 01646"},{"key":"ref43","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09199872.pdf?arnumber=9199872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:58Z","timestamp":1639770958000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9199872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3024639","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}