{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:21Z","timestamp":1778048301075,"version":"3.51.4"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00301","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3077-3087","source":"Crossref","is-referenced-by-count":0,"title":["GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving"],"prefix":"10.1109","author":[{"given":"William","family":"Ljungbergh","sequence":"first","affiliation":[{"name":"Zenseact"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Lilja","sequence":"additional","affiliation":[{"name":"Zenseact"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Tonderski","sequence":"additional","affiliation":[{"name":"Zenseact"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arvid Laveno","family":"Ling","sequence":"additional","affiliation":[{"name":"Zenseact"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carl","family":"Lindstr\u00f6m","sequence":"additional","affiliation":[{"name":"Zenseact"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Willem","family":"Verbeke","sequence":"additional","affiliation":[{"name":"Zenseact"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junsheng","family":"Fu","sequence":"additional","affiliation":[{"name":"Zenseact"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoffer","family":"Petersson","sequence":"additional","affiliation":[{"name":"Zenseact"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars","family":"Hammarstrand","sequence":"additional","affiliation":[{"name":"Chalmers University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Felsberg","sequence":"additional","affiliation":[{"name":"Linköping University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00139"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01373"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01846"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref6","article-title":"BEit: BERT pre-training of image transformers","volume-title":"International Conference on Learning Representations","author":"Bao"},{"key":"ref7","article-title":"Revisiting feature prediction for learning visual representations from video","author":"Bardes","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref10","article-title":"Nuplan: A closed-loop ml-based planning benchmark for autonomous vehicles","volume-title":"CVPR ADP3 workshop","author":"Caesar"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01417"},{"key":"ref13","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref15","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160831"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00039"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00727"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01101"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00930"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00114"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2005.09.002"},{"key":"ref31","article-title":"Semi-supervised vision-centric 3d occupancy world model for autonomous driving","volume-title":"ICLR","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01157"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02235-z"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02091"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00449"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02030"},{"key":"ref39","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref43","article-title":"Improving language understanding by generative pre-training","volume-title":"Technical report","author":"Radford","year":"2018"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref46","author":"Sykora","year":"2025","journal-title":"Personal correspondance."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01411"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2198"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01463"},{"key":"ref52","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks 2021)","author":"Wilson"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565009"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00798"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01443"},{"key":"ref56","article-title":"Emernerf: Emergent spatial-temporal scene decomposition via self-supervision","author":"Yang","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_26"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01390"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01161"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref62","article-title":"BEVWorld: A multimodal world model for autonomous driving via unified BEV latent space","author":"Zhang","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref64","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492247.pdf?arnumber=11492247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:55:33Z","timestamp":1778046933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492247\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00301","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}