{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T17:04:47Z","timestamp":1775581487940,"version":"3.50.1"},"reference-count":42,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672338"],"award-info":[{"award-number":["61672338"]}],"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":["61873160"],"award-info":[{"award-number":["61873160"]}],"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.2020.2975093","type":"journal-article","created":{"date-parts":[[2020,2,19]],"date-time":"2020-02-19T21:32:17Z","timestamp":1582147937000},"page":"35662-35671","source":"Crossref","is-referenced-by-count":53,"title":["Multimodal Encoder-Decoder Attention Networks for Visual Question Answering"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0521-0184","authenticated-orcid":false,"given":"Chongqing","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9392-9262","authenticated-orcid":false,"given":"Dezhi","family":"Han","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref38","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref33","article-title":"Simple baseline for visual question answering","author":"zhou","year":"2015","journal-title":"arXiv 1512 02167"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref37","article-title":"Layer normalization","author":"lei ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref35","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc AISTATS"},{"key":"ref34","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2016","journal-title":"arXiv 1610 04325"},{"key":"ref10","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014","journal-title":"Proc NIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/512"},{"key":"ref12","first-page":"1567","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Proc NIPS"},{"key":"ref13","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref18","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref4","article-title":"Multimodal unified attention networks for Vision-and-Language interactions","author":"yu","year":"2019","journal-title":"arXiv 1908 04107"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451103"},{"key":"ref3","first-page":"6639","article-title":"Dynamic fusion with Intra- and inter-modality attention flow for visual question answering","author":"gao","year":"2019","journal-title":"Proc CVPR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.743"},{"key":"ref5","article-title":"Multi-modality latent interaction network for visual question answering","author":"gao","year":"2019","journal-title":"arXiv 1908 04289"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref7","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generationwith visual attention","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref42","article-title":"Learning to count objects in natural images for visual question answering","author":"zhang","year":"2018","journal-title":"arXiv 1802 25766"},{"key":"ref24","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"},{"key":"ref41","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref25","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09003229.pdf?arnumber=9003229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:51:46Z","timestamp":1639770706000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003229\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2975093","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}