{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T20:48:11Z","timestamp":1781383691395,"version":"3.54.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1109\/lra.2021.3062324","type":"journal-article","created":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T20:37:24Z","timestamp":1614285444000},"page":"2830-2837","source":"Crossref","is-referenced-by-count":91,"title":["OmniDet: Surround View Cameras Based Multi-Task Visual Perception Network for Autonomous Driving"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8596-7629","authenticated-orcid":false,"given":"Varun","family":"Ravi Kumar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3755-4245","authenticated-orcid":false,"given":"Senthil","family":"Yogamani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hazem","family":"Rashed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ganesh","family":"Sitsu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Witt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isabelle","family":"Leang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Milz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6871-2707","authenticated-orcid":false,"given":"Patrick","family":"Mader","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202211"},{"key":"ref33","article-title":"On the Variance of the Adaptive Learning Rate and Beyond","author":"liu","year":"0","journal-title":"Int Conf Learn Represent (ICLR)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01142"},{"key":"ref31","first-page":"9605","article-title":"An intriguing failing of convolutional neural networks and the coordconv solution","author":"liu","year":"0","journal-title":"Proc Conf Neural Inf Proc Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01210"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref35","first-page":"3354","author":"geiger","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref34","first-page":"593","article-title":"Lookahead optimizer: K steps forward, 1 step back","author":"zhang","year":"0","journal-title":"Proc Conf Neural Inf Proc Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref40","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"eigen","year":"0","journal-title":"Proc Conf Neural Inf Proc Syst"},{"key":"ref11","first-page":"572","article-title":"Feature-metric loss for self-supervised learning of depth and egomotion","author":"shu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00446"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref14","first-page":"61","article-title":"SynDistNet: Self-supervised monocular fisheye camera distance estimation synergized with semantic segmentation for autonomous driving","author":"kumar","year":"0","journal-title":"Proc Conf Appl Comput Vis"},{"key":"ref15","first-page":"2272","article-title":"Generalized object detection on fisheye cameras for autonomous driving: Dataset, representations and baseline","author":"rashed","year":"0","journal-title":"Proc Conf Appl Comput Vis"},{"key":"ref16","article-title":"Poly-YOLO: Higher speed, more precise detection and instance segmentation for YOLOv3","author":"hurtik","year":"0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/34.31447"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3138\/FM57-6770-U75U-7727"},{"key":"ref19","article-title":"Yolov3: An incremental improvement","author":"redmon","year":"0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_10"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00159"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2021.3054719","article-title":"Multi-task learning for dense prediction tasks: A Survey","author":"vandenhende","year":"2021","journal-title":"IEEE Trans Pattern Analysis Mach Intell"},{"key":"ref6","article-title":"FisheyeMultiNet: Real-time multi-task learning architecture for surround-view automated parking system","author":"maddu","year":"2019","journal-title":"Irish Mach Vis Image Process Conf"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00940"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500504"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569744"},{"key":"ref7","first-page":"67","article-title":"SoilingNet: Soiling detection on automotive surround-view cameras","author":"u?i?\u00e1?","year":"0","journal-title":"Proc IEEE Intell Transp Syst Conf"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917043"},{"key":"ref9","first-page":"574","article-title":"FisheyeDistanceNet: Self-supervised scale-aware distance estimation using monocular fisheye camera for autonomous driving","author":"kumar","year":"0","journal-title":"Proc Int Conf Robot Automat"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340732"},{"key":"ref46","first-page":"1983","article-title":"GeoNet: Unsupervised learning of dense depth","author":"yin","year":"0","journal-title":"Optical Flow and Camera Pose"},{"key":"ref20","first-page":"4413","article-title":"The lovász-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks","author":"berman","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00716"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01252"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018001"},{"key":"ref24","first-page":"794","article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","author":"chen","year":"2018","journal-title":"ICML PMLR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00012"},{"key":"ref23","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","author":"kendall","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_17"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9285111\/09363560.pdf?arnumber=9363560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:57Z","timestamp":1652194437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9363560\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":47,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3062324","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}