{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:16:52Z","timestamp":1787012212251,"version":"build-2736575974"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001602","name":"Science Foundation Ireland (SFI)","doi-asserted-by":"publisher","award":["SFI 18\/CRT\/6049,16\/RI\/3399"],"award-info":[{"award-number":["SFI 18\/CRT\/6049,16\/RI\/3399"]}],"id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9891987","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T15:56:04Z","timestamp":1664553364000},"page":"1-7","source":"Crossref","is-referenced-by-count":18,"title":["ViT-BEVSeg: A Hierarchical Transformer Network for Monocular Birds-Eye-View Segmentation"],"prefix":"10.1109","author":[{"given":"Pramit","family":"Dutta","sequence":"first","affiliation":[{"name":"Hamilton Institute, Maynooth University,Dept of CS,Dublin,Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ganesh","family":"Sistu","sequence":"additional","affiliation":[{"name":"Valeo Vision Systems,Computer Vision Department,Galway,Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Senthil","family":"Yogamani","sequence":"additional","affiliation":[{"name":"Valeo Vision Systems,Computer Vision Department,Galway,Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edgar","family":"Galvan","sequence":"additional","affiliation":[{"name":"Maynooth University,Department of Computer Science,Dublin,Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"McDonald","sequence":"additional","affiliation":[{"name":"Maynooth University,Department of Computer Science,Dublin,Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00526"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00081"},{"key":"ref30","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref37","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref36","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"xie","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4414861"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.118"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","article-title":"Spatial transformer networks","volume":"28","author":"jaderberg","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.02.003"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/s120404431"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891028"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00655"},{"key":"ref28","article-title":"Real-time joint object detection and semantic segmentation network for automated driving","author":"sistu","year":"0","journal-title":"NeurIPS 2018 Workshop on ML on the Phone and other Consumer Devices"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref27","first-page":"10","article-title":"Analytical review of standard Sae J3016 taxonomy and definitions for terms related to driving automation systems for on-road motor vehicles with latest updates","volume":"3","author":"shadrin","year":"2019","journal-title":"Avtomobil &#x2018; Doroga Infrastruktura"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5220\/0007684106450652"},{"key":"ref6","author":"dwivedi","year":"2021","journal-title":"Bird's eye view segmentation using lifted 2d semantic features"},{"key":"ref29","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref5","article-title":"An image is worth 16&#x00D7;16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Bird'View Panoptic Segmentation Using Monocular Frontal View Images","author":"gosala","year":"0","journal-title":"IEEE l of Robotics and Automation"},{"key":"ref7","article-title":"A stochastic spatial representation for Active Robot Perception","author":"elfes","year":"1990","journal-title":"Proc on the sixth Conference on Uncertainty and AI AAAI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569710"},{"key":"ref9","article-title":"A survey on visual transformer","author":"han","year":"2020","journal-title":"ArXiv e-prints"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004325"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340732"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00232"},{"key":"ref26","article-title":"Orthographic feature transform for monocular 3d object detection","author":"roddick","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01115"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09891987.pdf?arnumber=9891987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T19:00:43Z","timestamp":1667502043000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9891987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9891987","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}