{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:27:06Z","timestamp":1780676826701,"version":"3.54.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,15]]},"DOI":"10.1109\/fg52635.2021.9667055","type":"proceedings-article","created":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T05:34:23Z","timestamp":1643175263000},"page":"1-8","source":"Crossref","is-referenced-by-count":43,"title":["Cross Attentional Audio-Visual Fusion for Dimensional Emotion Recognition"],"prefix":"10.1109","author":[{"given":"R. Gnana","family":"Praveen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Granger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Cardinal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811640"},{"key":"ref38","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"ACAI"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3428690.3429153"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-200","article-title":"Efficient emotion recognition from speech using deep learning on spectrograms","author":"satt","year":"2017","journal-title":"InterSpeech"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2228"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811642"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3264869.3264873"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811641"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383573"},{"key":"ref12","article-title":"Cross attention network for few-shot classification","author":"hou","year":"2019","journal-title":"NIPS"},{"key":"ref13","article-title":"Cross-attentional audio-visual fusion for weakly-supervised action localization","author":"lee","year":"2021","journal-title":"ICLRE"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914655"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063612"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2312"},{"key":"ref18","article-title":"Multimodal Emotion Recognition Using Cross-Modal Attention and 1D Convolutional Neural Networks","author":"n","year":"2020","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.77"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.03.001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.538"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.007"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-1456-2_7"},{"key":"ref5","article-title":"Emotion recognition in the wild with feature fusion and multiple kernel leaming","author":"chen","year":"2014","journal-title":"ICMI"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.10.011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2014.11"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9368-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00109"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5364"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: A survey and taxonomy","volume":"41","author":"baltru\u0161aitis","year":"2019","journal-title":"IEEE PAMI"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3417960"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.11.020"},{"key":"ref23","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2695999"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3024218"}],"event":{"name":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","location":"Jodhpur, India","start":{"date-parts":[[2021,12,15]]},"end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9666787\/9666788\/09667055.pdf?arnumber=9667055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:55:29Z","timestamp":1652201729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9667055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/fg52635.2021.9667055","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}