{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:16:07Z","timestamp":1775578567723,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0160400"],"award-info":[{"award-number":["2022ZD0160400"]}]},{"name":"Funds of China Scholarship Council","award":["201909120012"],"award-info":[{"award-number":["201909120012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3241517","type":"journal-article","created":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T19:55:49Z","timestamp":1675367749000},"page":"8753-8766","source":"Crossref","is-referenced-by-count":58,"title":["Textual Context-Aware Dense Captioning With Diverse Words"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7824-0985","authenticated-orcid":false,"given":"Zhuang","family":"Shao","sequence":"first","affiliation":[{"name":"Warwick Manufacturing Group, University of Warwick, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4361-956X","authenticated-orcid":false,"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Sheffield, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2982-5199","authenticated-orcid":false,"given":"Kurt","family":"Debattista","sequence":"additional","affiliation":[{"name":"Warwick Manufacturing Group, University of Warwick, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3727","authenticated-orcid":false,"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2942480"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref6","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref8","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3106641"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref12","first-page":"3613","article-title":"Diverse image captioning with context-object split latent spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ahajan","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_22"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018650"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00640"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.214"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3152990"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/PARC49193.2020.236619"},{"key":"ref22","first-page":"595","article-title":"Multimodal neural language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kiros","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941820"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00924"},{"key":"ref30","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2950526"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2502579"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016"},{"key":"ref37","first-page":"3440","article-title":"Adaptive minimax regret against smooth logarithmic losses over high-dimensional l1-balls via envelope complexity","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Miyaguchi","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537337"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10176-7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5532-x"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3043084"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.048"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10035421.pdf?arnumber=10035421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:02:42Z","timestamp":1703030562000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10035421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3241517","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}