{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:23:48Z","timestamp":1772907828100,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ARC Discovery Project","award":["DP200100938"],"award-info":[{"award-number":["DP200100938"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1109\/tcsvt.2020.2965966","type":"journal-article","created":{"date-parts":[[2020,1,14]],"date-time":"2020-01-14T23:01:33Z","timestamp":1579042893000},"page":"3413-3421","source":"Crossref","is-referenced-by-count":30,"title":["Cascaded Revision Network for Novel Object Captioning"],"prefix":"10.1109","volume":"30","author":[{"given":"Qianyu","family":"Feng","sequence":"first","affiliation":[]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Hehe","family":"Fan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1204-0512","authenticated-orcid":false,"given":"Chenggang","family":"Yan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6885-3451","authenticated-orcid":false,"given":"Mingliang","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc NIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00808"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_10"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.88"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.636"},{"key":"ref34","article-title":"Zero-shot learning—A comprehensive evaluation of the good, the bad and the ugly","author":"xian","year":"2017","journal-title":"Proc CVPR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref40","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc CVPR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240640"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2050411"},{"key":"ref15","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Proc NIPS"},{"key":"ref16","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","author":"mao","year":"2015","journal-title":"Proc ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/592"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1049\/el.2017.3159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/84"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2270402"},{"key":"ref29","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2736553"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2637778"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.8"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref20","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref45","first-page":"7310","article-title":"Speed\/accuracy trade-offs for modern convolutional object detectors","author":"huang","year":"2016","journal-title":"Proc CVPR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.291"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2903661"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.559"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2602938"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.130"},{"key":"ref23","article-title":"Image caption with global-local attention","author":"li","year":"2017","journal-title":"Proc AAAI"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2589859"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1098"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018965"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9210915\/08957311.pdf?arnumber=8957311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:31Z","timestamp":1651070371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8957311\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":47,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2020.2965966","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}