{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T03:42:55Z","timestamp":1752550975131,"version":"3.37.3"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61806213","U1435222"],"award-info":[{"award-number":["61806213","U1435222"]}],"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":[[2019]]},"DOI":"10.1109\/access.2019.2917979","type":"journal-article","created":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T15:31:02Z","timestamp":1558366262000},"page":"66680-66688","source":"Crossref","is-referenced-by-count":16,"title":["Cascade Semantic Fusion for Image Captioning"],"prefix":"10.1109","volume":"7","author":[{"given":"Shiwei","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4238-8985","authenticated-orcid":false,"given":"Long","family":"Lan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guohua","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhigang","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126717"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_21"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451083"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref17","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref19","first-page":"793","article-title":"Image captioning with visual-semantic LSTM","author":"li","year":"2018","journal-title":"Proc Int Joint Artif Intell Conf"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref27","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref29","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"arXiv 1705 03122"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref8","article-title":"Areas of attention for image captioning","author":"pedersoli","year":"2016","journal-title":"arXiv 1612 01033"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-4593-1"},{"key":"ref1","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2014","journal-title":"arXiv 1412 6632"},{"key":"ref46","first-page":"65","article-title":"METEOR: An automatic metric for mt evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref45","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref22","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref47","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Workshop on Text Summarization Branches Out"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.684"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.138"},{"key":"ref24","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref41","first-page":"4133","article-title":"Image caption with global-local attention","author":"li","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref23","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","author":"anderson","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref25","first-page":"1","article-title":"Multi-channel encoder for neural machine translation","author":"xiong","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08718598.pdf?arnumber=8718598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:54:32Z","timestamp":1641988472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8718598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2917979","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}