{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:07:17Z","timestamp":1740100037162,"version":"3.37.3"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,5]]},"DOI":"10.1109\/icme51207.2021.9428353","type":"proceedings-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T21:14:21Z","timestamp":1623273261000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Show, Rethink, And Tell: Image Caption Generation With Hierarchical Topic Cues"],"prefix":"10.1109","author":[{"given":"Feng","family":"Chen","sequence":"first","affiliation":[{"name":"National University of Defense Technology,Changsha,P. R. China,410073"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songxian","family":"Xie","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,P. R. China,410073"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyi","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,P. R. China,410073"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jintao","family":"Tang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,P. R. China,410073"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunyuan","family":"Pang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,P. R. China,410073"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shasha","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,P. R. China,410073"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,P. R. China,410073"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref13","article-title":"Latent dirichlet allocation","author":"blei","year":"2003","journal-title":"JMLR"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref14"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12266","article-title":"Stack-captioning: Coarse-to-fine learning for image captioning","author":"gu","year":"2018","journal-title":"AAAI"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref17","article-title":"Fine-grained image captioning with global-local discriminative objective","author":"wu","year":"2020","journal-title":"TMM"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3004729"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00483"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","article-title":"Image captioning and visual question answering based on attributes and external knowledge","author":"wu","year":"2017","journal-title":"TPAMI"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018320"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2019.00083"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref2","first-page":"1","article-title":"Nonnegative constrained graph based canonical correlation analysis for multi-view feature learning","author":"tan","year":"2018","journal-title":"NPL"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7192-5"},{"key":"ref9","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Computer Science"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref22","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref21","article-title":"Adaptively aligned image captioning via adaptive attention time","author":"huang","year":"2019","journal-title":"NIPS"},{"key":"ref24","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"ACL"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref26","article-title":"Rouge: A package for automatic evaluation of summaries","author":"flick","year":"2004","journal-title":"Workshop on Text Summarization Branches Out"},{"key":"ref25","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"ACL2 Workshop"}],"event":{"name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2021,7,5]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,9]]}},"container-title":["2021 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9428049\/9428068\/09428353.pdf?arnumber=9428353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T13:58:11Z","timestamp":1672408691000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428353\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428353","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}