{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T03:00:36Z","timestamp":1768705236249,"version":"3.49.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"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":[[2024,10,2]]},"DOI":"10.1109\/mmsp61759.2024.10743612","type":"proceedings-article","created":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T18:35:35Z","timestamp":1731436535000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["MultiFuser: Multimodal Fusion Transformer for Enhanced Driver Action Recognition"],"prefix":"10.1109","author":[{"given":"Ruoyu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University,Singapore"}]},{"given":"Wenqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Continental-NTU Corporate Lab,Singapore"}]},{"given":"Jianjun","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University,Singapore"}]},{"given":"Dan","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Continental-NTU Corporate Lab,Singapore"}]},{"given":"Kim-Hui","family":"Yap","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University,Singapore"}]},{"given":"Bingbing","family":"Li","sequence":"additional","affiliation":[{"name":"Continental Automotive Singapore Pte. Ltd.,Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2021.3050883"},{"key":"ref2","article-title":"Trans-dare: Transformer-based driver activity recognition with latent space feature calibration","volume-title":"IROS","author":"Peng","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3304317"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CRV55824.2022.00011"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827426"},{"key":"ref7","article-title":"Real-time driver monitoring systems through modality and view analysis","author":"Ma","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_23"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3279991"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref13","first-page":"2801","article-title":"Drive&act: A multi-modal dataset for fine-grained driver behavior recognition in autonomous vehicles","volume-title":"ICCV","author":"Martin","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448437"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00157"},{"key":"ref18","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref20","first-page":"1279","article-title":"Coarse temporal attention network (eta-net) for driver\u2019s activity recognition","volume-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","author":"Wharton","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)","location":"West Lafayette, IN, USA","start":{"date-parts":[[2024,10,2]]},"end":{"date-parts":[[2024,10,4]]}},"container-title":["2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10743173\/10743194\/10743612.pdf?arnumber=10743612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T15:53:27Z","timestamp":1732722807000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10743612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,2]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/mmsp61759.2024.10743612","relation":{},"subject":[],"published":{"date-parts":[[2024,10,2]]}}}