{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:08:09Z","timestamp":1774627689017,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673062"],"award-info":[{"award-number":["61673062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072041"],"award-info":[{"award-number":["62072041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2020.3042086","type":"journal-article","created":{"date-parts":[[2020,12,11]],"date-time":"2020-12-11T21:35:57Z","timestamp":1607722557000},"page":"1180-1192","source":"Crossref","is-referenced-by-count":55,"title":["Cross-Domain Image Captioning via Cross-Modal Retrieval and Model Adaptation"],"prefix":"10.1109","volume":"30","author":[{"given":"Wentian","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2056-6947","authenticated-orcid":false,"given":"Xinxiao","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","first-page":"4278","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","volume":"2017","author":"szegedy","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref71","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00446"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/85"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.130"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00646"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821921"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2564638"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132920"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2880185"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.435"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00648"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref64","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"wah","year":"2011"},{"key":"ref27","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref29","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015","journal-title":"arXiv 1511 06732"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref69","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01042"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/128"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00751"},{"key":"ref26","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref25","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01186"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2890628"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963950"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940677"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2902106"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2859820"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6820"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref11","article-title":"Explain images with multimodal recurrent neural networks","author":"mao","year":"2014","journal-title":"arXiv 1410 1090"},{"key":"ref40","first-page":"1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916757"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref18","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref4","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref5","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref8","first-page":"15","article-title":"Every picture tells a story: Generating sentences from images","author":"farhadi","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.64"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref9","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","author":"li","year":"2011","journal-title":"Proc 15th Conf Comput Natural Lang Learn"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2965987"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351067"},{"key":"ref42","first-page":"12","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref41","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.261"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09292444.pdf?arnumber=9292444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:09Z","timestamp":1652194209000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9292444\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.3042086","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}