{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:06:49Z","timestamp":1780949209414,"version":"3.54.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20342"],"award-info":[{"award-number":["U24A20342"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102205"],"award-info":[{"award-number":["62102205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Anhui Provincial Natural Science Foundation-Outstanding Youth Project","doi-asserted-by":"publisher","award":["2408085Y032"],"award-info":[{"award-number":["2408085Y032"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcsvt.2026.3663409","type":"journal-article","created":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T21:06:49Z","timestamp":1770757609000},"page":"8615-8630","source":"Crossref","is-referenced-by-count":1,"title":["Vehicle-Centric Perception via Multimodal Structured Pre-Training"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0120-6472","authenticated-orcid":false,"given":"Wentao","family":"Wu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-6745","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7233-2739","authenticated-orcid":false,"given":"Chenglong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, the State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8375-3590","authenticated-orcid":false,"given":"Jin","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5948-5055","authenticated-orcid":false,"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3151116"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3502136"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3427720"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3531883"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3454366"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","first-page":"611","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3462433"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01445"},{"key":"ref10","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref11","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref12","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref13","volume-title":"GPT-4 Technical Report","year":"2023"},{"key":"ref14","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref16","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28373"},{"key":"ref21","article-title":"VFM-Det: Towards high-performance vehicle detection via large foundation models","author":"Wu","year":"2024","journal-title":"arXiv:2408.13031"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402109"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-025-01747-z"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.02.021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref28","first-page":"16433","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bao"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110975"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32324"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02085"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3436029"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3583168"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755717"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402952"},{"key":"ref36","article-title":"PLIP: Language-image pre-training for person representation learning","author":"Zuo","year":"2023","journal-title":"arXiv:2305.08386"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00489"},{"key":"ref38","article-title":"Pre-training on high definition X-ray images: An experimental study","author":"Wang","year":"2024","journal-title":"arXiv:2404.17926"},{"key":"ref39","article-title":"RoMA: Scaling up mamba-based foundation models for remote sensing","author":"Wang","year":"2025","journal-title":"arXiv:2503.10392"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.00921"},{"key":"ref41","first-page":"894","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178144"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28419"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00043"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01200"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3695255"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/s22208027"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007074"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3573396"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02608"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02362"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref56","first-page":"4639","article-title":"Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.68"},{"key":"ref58","article-title":"SODA10M: A large-scale 2D self\/semi-supervised object detection dataset for autonomous driving","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. (NeurIPS) Datasets Benchmarks Track","author":"Han"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_53"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_8"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref63","first-page":"4061","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11390719.pdf?arnumber=11390719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:30Z","timestamp":1780948470000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11390719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":65,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3663409","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}