{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:21:10Z","timestamp":1783527670572,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/tmm.2018.2888822","type":"journal-article","created":{"date-parts":[[2018,12,20]],"date-time":"2018-12-20T19:47:51Z","timestamp":1545335271000},"page":"1681-1693","source":"Crossref","is-referenced-by-count":63,"title":["High-Quality Image Captioning With Fine-Grained and Semantic-Guided Visual Attention"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9309-1826","authenticated-orcid":false,"given":"Zongjian","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref33","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"0","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref31","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"ref36","first-page":"940","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.334"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.214"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.130"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.681"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.559"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.272"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751140"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2644872"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482228"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00190"},{"key":"ref29","first-page":"824","article-title":"DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"chen","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2642789"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2847248"},{"key":"ref9","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref46","first-page":"2407","article-title":"Guiding the longshort term memory model for image caption generation","author":"jia","year":"0","journal-title":"Proc Int Conf Comput Vis"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref47","first-page":"1000","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref42","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2191944"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2684626"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126717"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref25","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8743377\/08584101.pdf?arnumber=8584101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:06:35Z","timestamp":1657746395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8584101\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":48,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2888822","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7]]}}}