{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T07:28:08Z","timestamp":1775892488559,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956730","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T14:34:13Z","timestamp":1669732453000},"page":"2582-2588","source":"Crossref","is-referenced-by-count":25,"title":["Audio and Video-based Emotion Recognition using Multimodal Transformers"],"prefix":"10.1109","author":[{"given":"Vijay","family":"John","sequence":"first","affiliation":[{"name":"Guardian Robot Project, R-IH,RIKEN,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasutomo","family":"Kawanishi","sequence":"additional","affiliation":[{"name":"Guardian Robot Project, R-IH,RIKEN,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Emotion recognition in audio and video using deep neural networks","author":"singh","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.102"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref13","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proceedings of the 31st Annual Conference on Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref15","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref16","article-title":"Using large pre-trained models with cross-modal attention for multi-modal emotion recognition","author":"krishna","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0196391","article-title":"The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English","volume":"13","author":"livingstone","year":"2018","journal-title":"PLoS ONE"},{"key":"ref19","first-page":"398","author":"haq","year":"2010","journal-title":"Machine Audition Principles Algorithms and Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993185"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997637"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-200"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264978"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/TAFFC.2017.2740923","article-title":"Affectnet: A database for facial expression, valence, and arousal computing in the wild","volume":"10","author":"mollahosseini","year":"2019","journal-title":"IEEE Transactions on Affective Computing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3417968"},{"key":"ref7","article-title":"Emotion recognition system from speech and visual information based on convolutional neural networks","author":"ristea","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.007"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2713783"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-57"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref23","article-title":"Audio-video emotion recognition in the wild using deep hybrid networks","author":"guo","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.26"},{"key":"ref25","article-title":"CNN architectures for large-scale audio classification","author":"hershey","year":"2016"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956730.pdf?arnumber=9956730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T15:05:25Z","timestamp":1671462325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956730","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}