{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T07:15:09Z","timestamp":1770275709730,"version":"3.49.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"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":[[2025,5,26]]},"DOI":"10.1109\/fg61629.2025.11099454","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:55:00Z","timestamp":1754502900000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Cross-modal Emotion-specific Attention model for Multimodal Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Jia-Yi","family":"Chen","sequence":"first","affiliation":[{"name":"RIKEN Guardian Robot Project, RIKEN,Kyoto,Japan"}]},{"given":"Vijay","family":"John","sequence":"additional","affiliation":[{"name":"RIKEN Guardian Robot Project, RIKEN,Kyoto,Japan"}]},{"given":"Yasutomo","family":"Kawanishi","sequence":"additional","affiliation":[{"name":"RIKEN Guardian Robot Project, RIKEN,Kyoto,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ATSIP55956.2022.9805924"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00470"},{"key":"ref4","article-title":"An image is worth 16 times 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv:2010.11929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2371456.2371474"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref9","first-page":"28708","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.04.010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956730"},{"key":"ref12","article-title":"Facial emotion recognition: State of the art performance on FER2013","author":"Khaireddin","year":"2021","journal-title":"arXiv preprint arXiv:2105.03588"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref14","article-title":"Decoupled weight decay regularization","volume-title":"Proceedings of the 2019 International Conference on Learning Representations (ICLR)","author":"Loshchilov"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00630"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s42452-020-2234-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02567"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906538"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0940-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IMITEC45504.2019.9015895"},{"key":"ref22","article-title":"Emotion recognition in audio and video using deep neural networks","author":"Singh","year":"2020","journal-title":"arXiv preprint arXiv:2006.08129"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICAECA52838.2021.9675492"},{"key":"ref24","volume-title":"Learning face representation from scratch","author":"Yi","year":"2014"},{"key":"ref25","volume-title":"Face transformer for recognition","author":"Zhong","year":"2021"}],"event":{"name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Tampa\/Clearwater, FL, USA","start":{"date-parts":[[2025,5,26]]},"end":{"date-parts":[[2025,5,30]]}},"container-title":["2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11099084\/11099070\/11099454.pdf?arnumber=11099454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:41:40Z","timestamp":1754588500000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11099454\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,26]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/fg61629.2025.11099454","relation":{},"subject":[],"published":{"date-parts":[[2025,5,26]]}}}