{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T08:28:29Z","timestamp":1776155309441,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"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":["2018AAA0100603"],"award-info":[{"award-number":["2018AAA0100603"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702143"],"award-info":[{"award-number":["61702143"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836002"],"award-info":[{"award-number":["61836002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1109\/tcsvt.2019.2947482","type":"journal-article","created":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T22:21:57Z","timestamp":1571178117000},"page":"4467-4480","source":"Crossref","is-referenced-by-count":379,"title":["Multimodal Transformer With Multi-View Visual Representation for Image Captioning"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5639-4289","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8407-1137","authenticated-orcid":false,"given":"Zhou","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2307862"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref30","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref34","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00646"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609563"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref50","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2889922"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2928144"},{"key":"ref54","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":"ref53","first-page":"1","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref11","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2830102"},{"key":"ref12","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref14","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref16","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"2012","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref17","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"2011","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref18","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref3","first-page":"1564","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867286"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref46","first-page":"1","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc 42nd Ann Meeting of the Assoc for Computational Linguistics"},{"key":"ref45","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref47","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2726580"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9280452\/08869845.pdf?arnumber=8869845","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\/8869845\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":60,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2019.2947482","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12]]}}}