{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T10:17:44Z","timestamp":1779877064427,"version":"3.53.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746418","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"4573-4577","source":"Crossref","is-referenced-by-count":45,"title":["Mmlatch: Bottom-Up Top-Down Fusion For Multimodal Sentiment Analysis"],"prefix":"10.1109","author":[{"given":"Georgios","family":"Paraskevopoulos","sequence":"first","affiliation":[{"name":"National Technical University of Athens,Athens,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Efthymios","family":"Georgiou","sequence":"additional","affiliation":[{"name":"National Technical University of Athens,Athens,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandras","family":"Potamianos","sequence":"additional","affiliation":[{"name":"National Technical University of Athens,Athens,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053012"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref33","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31st NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1827"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2482"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.challengehml-1.1"},{"key":"ref35","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc 32nd NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref10","article-title":"Top-down effects in visual","volume":"2","author":"bar","year":"2013","journal-title":"Oxford Handbook of Cognitive Neuroscience"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.143"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.concog.2016.05.008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.5069-11.2012"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1037\/xhp0000343"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0956797609356283"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3758\/BF03210980"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0956797613485092"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.06.004"},{"key":"ref18","article-title":"Ensemble of svm trees for multimodal emotion recognition","author":"rozgi?","year":"2012","journal-title":"Proc APSIPA IEEE"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.40"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1207"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.216"},{"key":"ref27","article-title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","author":"zadeh","year":"2018","journal-title":"Proc 56th ACL"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1422"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2011.04.015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3243"},{"key":"ref5","article-title":"Multi-modal speech recognition with unstructured audio masking","author":"srinivasan","year":"2020","journal-title":"Proc 1st Workshop on NLPBT"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2015.04.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-7687.2006.00512.x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbr.2019.112214"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref46","article-title":"Lightweight models for multimodal sequential data","author":"sourav","year":"2021","journal-title":"Proc 11th WASSA"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.03.001"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0055"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.challengehml-1.3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref41","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Proc 30th NeurIPS"},{"key":"ref23","article-title":"Multimodal machine learning: A survey and taxonomy","author":"baltru\u0161aitis","year":"2018","journal-title":"Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","author":"diederik","year":"2015","journal-title":"The 3rd ICLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01096"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746418.pdf?arnumber=9746418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:15:07Z","timestamp":1661199307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746418\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746418","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}