{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T09:38:50Z","timestamp":1776418730488,"version":"3.51.2"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin City","doi-asserted-by":"publisher","award":["19JCYBJC16000"],"award-info":[{"award-number":["19JCYBJC16000"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771329"],"award-info":[{"award-number":["61771329"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2975594","type":"journal-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T21:03:41Z","timestamp":1582319021000},"page":"38438-38447","source":"Crossref","is-referenced-by-count":16,"title":["Multi-Modal Memory Enhancement Attention Network for Image-Text Matching"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2197-3739","authenticated-orcid":false,"given":"Zhong","family":"Ji","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhigang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1666-4330","authenticated-orcid":false,"given":"Yuqing","family":"He","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref33","article-title":"Dual-path convolutional image-text embedding with instance loss","author":"zheng","year":"2017","journal-title":"arXiv 1711 05535"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882225"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00601"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref29","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and VQA","author":"anderson","year":"2018","journal-title":"IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref2","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":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1194140"},{"key":"ref20","article-title":"Neural turing machines","author":"graves","year":"2014","journal-title":"arXiv 1410 5401"},{"key":"ref22","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"ref26","first-page":"935","article-title":"VSE++: Improved visual semantic embeddings","author":"fartash","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref25","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2897249"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2966220"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00921"},{"key":"ref11","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.178"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00429"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.038"},{"key":"ref6","first-page":"1","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst Workshop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.05.008"},{"key":"ref8","first-page":"1","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref7","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":"ref49","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv 1301 3781 [cs]"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_24"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref42","first-page":"2121","article-title":"Devise: A deep visualsemantic embedding model","author":"frome","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"1","article-title":"Memory networks","author":"weston","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref44","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","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"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09006782.pdf?arnumber=9006782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T20:08:55Z","timestamp":1662667735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9006782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2975594","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}