{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T20:30:18Z","timestamp":1771533018303,"version":"3.50.1"},"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\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61575090"],"award-info":[{"award-number":["61575090"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China Youth Fund","doi-asserted-by":"publisher","award":["61803189"],"award-info":[{"award-number":["61803189"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","award":["2019-ZD-0031"],"award-info":[{"award-number":["2019-ZD-0031"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","award":["2020FWDF13"],"award-info":[{"award-number":["2020FWDF13"]}],"id":[{"id":"10.13039\/501100005047","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.2021.3057091","type":"journal-article","created":{"date-parts":[[2021,2,6]],"date-time":"2021-02-06T01:21:27Z","timestamp":1612574487000},"page":"25360-25370","source":"Crossref","is-referenced-by-count":4,"title":["An Image Captioning Model Based on Bidirectional Depth Residuals and its Application"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2958-3778","authenticated-orcid":false,"given":"Ziwei","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1864-5961","authenticated-orcid":false,"given":"Liang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1750-5825","authenticated-orcid":false,"given":"Chaoyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8263-9868","authenticated-orcid":false,"given":"Wei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4353-8105","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8413-576X","authenticated-orcid":false,"given":"Shaoqiang","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7438-7637","authenticated-orcid":false,"given":"Ye","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref33","article-title":"Residual LSTM: Design of a deep recurrent architecture for distant speech recognition","author":"kim","year":"2017","journal-title":"arXiv 1701 03360"},{"key":"ref32","first-page":"2377","article-title":"Training very deep networks","volume":"28","author":"srivastava","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2116010"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref36","first-page":"26","article-title":"Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref35","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1007\/978-3-642-35289-8_25","article-title":"Stochastic gradient descent tricks","author":"bottou","year":"2012","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref40","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.12.025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-019-01774-8"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-019-8123-3","article-title":"A correlative denoising autoencoder to model social influence for top-N recommender system","volume":"14","author":"pan","year":"2020","journal-title":"Frontiers Comput Sci"},{"key":"ref15","first-page":"1","article-title":"A multi-phase blending method with incremental intensity for training detection networks","author":"quan","year":"2020","journal-title":"Vis Comput"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref17","first-page":"15","article-title":"Every picture tells a story: Generating sentences from images","author":"farhadi","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00898"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref42","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.130"},{"key":"ref41","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2012","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref23","first-page":"2204","article-title":"Recurrent models of visual attention","volume":"27","author":"mnih","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref26","first-page":"684","article-title":"Exploring visual relationship for image captioning","author":"yao","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09347457.pdf?arnumber=9347457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T12:05:08Z","timestamp":1643285108000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9347457\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3057091","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}