{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T17:22:56Z","timestamp":1791480176568,"version":"4.3.4"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"DREAM CDT"},{"name":"European Union\u2019s Horizon 2020 Research and Innovation Programme PROPAG-AGEING","award":["634821"],"award-info":[{"award-number":["634821"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1109\/tnnls.2019.2945992","type":"journal-article","created":{"date-parts":[[2019,11,8]],"date-time":"2019-11-08T21:32:37Z","timestamp":1573248757000},"page":"3711-3720","source":"Crossref","is-referenced-by-count":27,"title":["XFlow: Cross-Modal Deep Neural Networks for Audiovisual Classification"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5741-3744","authenticated-orcid":false,"given":"Catalina","family":"Cangea","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petar","family":"Velickovic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pietro","family":"Lio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/34.982900"},{"key":"ref11","first-page":"ii-2017","article-title":"CUAVE: A new audio-visual database for multimodal human-computer interface research","volume":"2","author":"patterson","year":"2002","journal-title":"Proc ICASSP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806216"},{"key":"ref13","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.538"},{"key":"ref15","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref16","article-title":"The mythos of model interpretability","author":"lipton","year":"2016","journal-title":"arXiv 1606 03490"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2998574"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2375793"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2390499"},{"key":"ref4","article-title":"X-CNN: Cross-modal convolutional neural networks for sparse datasets","author":"veli?kovi?","year":"2016","journal-title":"arXiv 1610 00163"},{"key":"ref3","article-title":"See, hear, and read: Deep aligned representations","author":"aytar","year":"2017","journal-title":"arXiv 1706 00932"},{"key":"ref6","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv 1502 03167"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref7","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":"ref2","first-page":"2222","article-title":"Multimodal learning with deep boltzmann machines","author":"srivastava","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref1","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn (ICML)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2753232"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/96"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1293"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9184294\/08894404.pdf?arnumber=8894404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:19:49Z","timestamp":1651079989000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8894404\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9]]},"references-count":26,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2945992","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9]]}}}