{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T22:36:04Z","timestamp":1792794964771,"version":"4.5.0"},"reference-count":40,"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":["61602197"],"award-info":[{"award-number":["61602197"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Equipment Pre-Research Fund for the 13th Five-Year Plan","award":["41412050801"],"award-info":[{"award-number":["41412050801"]}]},{"DOI":"10.13039\/501100003397","name":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, Huazhong University of Science and Technology, Wuhan, China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003397","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3018752","type":"journal-article","created":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T20:47:24Z","timestamp":1598302044000},"page":"154953-154965","source":"Crossref","is-referenced-by-count":24,"title":["Stack-VS: Stacked Visual-Semantic Attention for Image Caption Generation"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2834-9728","authenticated-orcid":false,"given":"Ling","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4488-0102","authenticated-orcid":false,"given":"Wei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6795-2311","authenticated-orcid":false,"given":"Xianling","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9031-9696","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0300-3448","authenticated-orcid":false,"given":"Chunyan","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref33","first-page":"1","article-title":"Optimization of image description metrics using policy gradient methods","volume":"abs 1612 370","author":"liu","year":"2016","journal-title":"CoRR"},{"key":"ref32","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015","journal-title":"arXiv 1511 06732"},{"key":"ref31","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":"ref30","first-page":"21","article-title":"Gated hierarchical attention for image captioning","author":"wang","year":"2018","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref36","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Workshop on Text Summarization Branches Out"},{"key":"ref35","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref34","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref10","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref40","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"Proc ECCV"},{"key":"ref11","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","author":"li","year":"2011","journal-title":"Proc CoNLL"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICBK.2017.35"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/563"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2256797"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487700"},{"key":"ref28","first-page":"1","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","author":"mao","year":"2014","journal-title":"Proc ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref3","article-title":"Explain images with multimodal recurrent neural networks","author":"mao","year":"2014","journal-title":"arXiv 1410 1090"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref29","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"2016","journal-title":"Proc NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref7","article-title":"Learning to guide decoding for image captioning","author":"jiang","year":"2018","journal-title":"arXiv 1804 00887"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00177"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2892755"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref22","first-page":"1","article-title":"Stack-captioning: Coarse-to-fine learning for image captioning","author":"gu","year":"2018","journal-title":"Proc AAAI"},{"key":"ref21","article-title":"SCA-CNN: Spatial and channel-wise attention in convolutional networks for image captioning","author":"chen","year":"2016","journal-title":"arXiv 1611 05594"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2849417"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref25","first-page":"1","article-title":"Buried utility pipeline mapping based on multiple spatial data sources: A Bayesian data fusion approach","author":"chen","year":"2011","journal-title":"Proc Int Joint Conf Artif Intell"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09174742.pdf?arnumber=9174742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:23Z","timestamp":1639770923000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9174742\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3018752","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}