{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T08:22:21Z","timestamp":1770538941205,"version":"3.49.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.23919\/fusion45008.2020.9190483","type":"proceedings-article","created":{"date-parts":[[2020,9,10]],"date-time":"2020-09-10T21:24:07Z","timestamp":1599773047000},"page":"1-8","source":"Crossref","is-referenced-by-count":9,"title":["Multimodal Fusion with Co-attention Mechanism"],"prefix":"10.23919","author":[{"given":"Pei","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinde","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/1460096.1460104","article-title":"The mir flickr retrieval evaluation","author":"huiskes","year":"2008","journal-title":"Proceedings of the 1st ACM International Conference on Multimedia Information Retrieval"},{"key":"ref11","author":"simonyan","year":"0","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2864920"},{"key":"ref13","first-page":"2222","article-title":"Multimodal learning with deep boltzmann machines","author":"srivastava","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683898"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref6","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref1","first-page":"2141","article-title":"Improved multimodal deep learning with variation of information","author":"sohn","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"}],"event":{"name":"2020 IEEE 23rd International Conference on Information Fusion (FUSION)","location":"Rustenburg, South Africa","start":{"date-parts":[[2020,7,6]]},"end":{"date-parts":[[2020,7,9]]}},"container-title":["2020 IEEE 23rd International Conference on Information Fusion (FUSION)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9183728\/9190162\/09190483.pdf?arnumber=9190483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,31]],"date-time":"2021-03-31T19:42:55Z","timestamp":1617219775000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9190483\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":14,"URL":"https:\/\/doi.org\/10.23919\/fusion45008.2020.9190483","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}