{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:17:00Z","timestamp":1778080620343,"version":"3.51.4"},"reference-count":34,"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\/icassp43922.2022.9746006","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"4638-4642","source":"Crossref","is-referenced-by-count":20,"title":["Multi-View And Multi-Modal Event Detection Utilizing Transformer-Based Multi-Sensor Fusion"],"prefix":"10.1109","author":[{"given":"Masahiro","family":"Yasuda","sequence":"first","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasunori","family":"Ohishi","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoichiro","family":"Saito","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noboru","family":"Harado","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"1","article-title":"The real-world-weight cross-entropy loss function: Modeling the costs of mislabeling","author":"ho","year":"2019","journal-title":"IEEE Access"},{"key":"ref32","article-title":"Sound event detection and time-frequency segmentation from weakly labelled data","author":"kong","year":"2018","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.009"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref34","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc of International Conference on Learning Representations (ICLR)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690559"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref14","article-title":"Cross-view action recognition via a transferable dictionary pair","volume":"25","author":"zheng","year":"2012","journal-title":"IEEE Transactions on Image Processing"},{"key":"ref15","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1882992.1883032"},{"key":"ref4","first-page":"1","article-title":"Sound event localization and detection of overlapping sources using convolutional recurrent neural networks","author":"adavanne","year":"2018","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-017-0597-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00875"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004325"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref22","article-title":"Building generalizable agents with a realistic and rich 3d environment","author":"wu","year":"2018"},{"key":"ref21","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume":"78","author":"codevilla","year":"2017","journal-title":"Proc of the 1st Annual Conference on Robot Learning"},{"key":"ref24","article-title":"MMTM: Multimodal transfer module for cnn fusion","author":"joze","year":"2020","journal-title":"Proc of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref23","article-title":"CentralNet: a multi-layer approach for multimodal fusion","author":"vielzeuf","year":"2018","journal-title":"Proc of the European Conference on Computer Vision (ECCV) Workshops"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00713"}],"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\/09746006.pdf?arnumber=9746006","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:05:48Z","timestamp":1660579548000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746006\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746006","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}