{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:39:34Z","timestamp":1762522774457,"version":"3.37.3"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"EPSRC","doi-asserted-by":"publisher","award":["EP\/S016317\/1"],"award-info":[{"award-number":["EP\/S016317\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981835","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"2402-2408","source":"Crossref","is-referenced-by-count":6,"title":["AFT-VO: Asynchronous Fusion Transformers for Multi-View Visual Odometry Estimation"],"prefix":"10.1109","author":[{"given":"Nimet","family":"Kaygusuz","sequence":"first","affiliation":[{"name":"University of Surrey,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oscar","family":"Mendez","sequence":"additional","affiliation":[{"name":"University of Surrey,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Bowden","sequence":"additional","affiliation":[{"name":"University of Surrey,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"NeurIPS","author":"Akbari","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01079"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11215"},{"key":"ref6","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2658577"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460204"},{"volume-title":"evo: Python package for the evaluation of odometry and slam","year":"2017","author":"Grupp","key":"ref11"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2225"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636827"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565079"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461251"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593561"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/152280"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08338-4_25"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315094"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9698-5"},{"article-title":"Analysis of positional encodings for neural machine translation","volume-title":"IWSLT","author":"Rosendahl","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793581"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.2004640"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915571429"},{"key":"ref28","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917734298"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00877"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561481"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00043"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/s18114036"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981835.pdf?arnumber=9981835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:44:47Z","timestamp":1706759087000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981835\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981835","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}