{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:21:36Z","timestamp":1740100896192,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61966004"],"award-info":[{"award-number":["61966004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004607","name":"Guangxi Natural Science Foundation","doi-asserted-by":"publisher","award":["2019GXNSFDA245018"],"award-info":[{"award-number":["2019GXNSFDA245018"]}],"id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859885","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Dynamic Transformer for Image Captioning"],"prefix":"10.1109","author":[{"given":"Tiantao","family":"Xian","sequence":"first","affiliation":[{"name":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[{"name":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huifang","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Northwest Normal University,Lanzhou,China,730070"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.01.011"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00858"},{"key":"ref12","first-page":"11131","article-title":"Fine-grained dynamic head for object detection","author":"song","year":"2020","journal-title":"NIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref14","article-title":"A better variant of self-critical sequence training","author":"luo","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"NAACL"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428353"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref6","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3439734"},{"key":"ref8","article-title":"Improving image captioning by leveraging intra- and inter-layer global representation in transformer network","author":"ji","year":"0","journal-title":"AAAI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref2","article-title":"Exploring visual relationship for image captioning","author":"yao","year":"0","journal-title":"CVPR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref22","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref21","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"banerjee","year":"0","journal-title":"ACL2 Workshop"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2022,7,18]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859885.pdf?arnumber=9859885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:23:56Z","timestamp":1663619036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859885","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}