{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T03:29:23Z","timestamp":1775014163186,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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":[[2025,6,22]]},"DOI":"10.1109\/iv64158.2025.11097781","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:54:55Z","timestamp":1754502895000},"page":"345-350","source":"Crossref","is-referenced-by-count":1,"title":["BEV-LLM: Leveraging Multimodal BEV Maps for Scene Captioning in Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Felix","family":"Brandst\u00e4tter","sequence":"first","affiliation":[{"name":"Munich University of Applied Sciences,Intelligent Vehicles Lab (IVL),Munich,Germany,80335"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erik","family":"Sch\u00fctz","sequence":"additional","affiliation":[{"name":"Munich University of Applied Sciences,Intelligent Vehicles Lab (IVL),Munich,Germany,80335"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katharina","family":"Winter","sequence":"additional","affiliation":[{"name":"Munich University of Applied Sciences,Intelligent Vehicles Lab (IVL),Munich,Germany,80335"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabian B.","family":"Flohr","sequence":"additional","affiliation":[{"name":"Munich University of Applied Sciences,Intelligent Vehicles Lab (IVL),Munich,Germany,80335"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10421901"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"ref4","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu","year":"2022"},{"key":"ref6","article-title":"Emma: End-to-end multimodal model for autonomous driving","author":"Hwang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Senna: Bridging large vision-language models and end-to-end autonomous driving","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8850-1_38"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_21"},{"key":"ref10","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Wei-Jing","year":"2002","journal-title":"Technical report, IBM T. J. Watson Research Center"},{"key":"ref11","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","volume":"202","author":"Li"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575562"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32782"},{"key":"ref18","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. in NIPS"},{"key":"ref19","article-title":"Drivemlm: Aligning multi-modal large language models with behavioral planning states for autonomous driving","volume-title":"Proc. CoRR","author":"Wang","year":"2023"},{"key":"ref20","article-title":"Drivegpt4: In-terpretable end-to-end autonomous driving via large language model","author":"Xu","year":"2024","journal-title":"IEEE RA-L"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33001"},{"key":"ref22","article-title":"Rag-driver: Generalisable driving explanations with retrieval-augmented in-context learning in multi-modal large language model","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5755\/j01.itc.53.1.35095"},{"key":"ref24","article-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Bertscore: Evaluating text generation with bert","volume-title":"Proc. ICLR","author":"Zhang","year":"2020"},{"key":"ref26","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE Intelligent Vehicles Symposium (IV)","location":"Cluj-Napoca, Romania","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11097351\/11097337\/11097781.pdf?arnumber=11097781","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T05:16:14Z","timestamp":1754543774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11097781\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iv64158.2025.11097781","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}