{"ID":2843015,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.10701","arxiv_id":"2511.10701","title":"CARScenes: Semantic VLM Dataset for Safe Autonomous Driving","abstract":"CAR-Scenes is a frame-level dataset for autonomous driving that enables training and evaluation of vision-language models (VLMs) for interpretable, scene-level understanding. We annotate 5,192 images drawn from Argoverse 1, Cityscapes, KITTI, and nuScenes using a 28-key category/sub-category knowledge base covering environment, road geometry, background-vehicle behavior, ego-vehicle behavior, vulnerable road users, sensor states, and a discrete severity scale (1-10), totaling 350+ leaf attributes. Labels are produced by a GPT-4o-assisted vision-language pipeline with human-in-the-loop verification; we release the exact prompts, post-processing rules, and per-field baseline model performance. CAR-Scenes also provides attribute co-occurrence graphs and JSONL records that support semantic retrieval, dataset triage, and risk-aware scenario mining across sources. To calibrate task difficulty, we include reproducible, non-benchmark baselines, notably a LoRA-tuned Qwen2-VL-2B with deterministic decoding, evaluated via scalar accuracy, micro-averaged F1 for list attributes, and severity MAE/RMSE on a fixed validation split. We publicly release the annotation and analysis scripts, including graph construction and evaluation scripts, to enable explainable, data-centric workflows for future intelligent vehicles. Dataset: https://github.com/Croquembouche/CAR-Scenes","short_abstract":"CAR-Scenes is a frame-level dataset for autonomous driving that enables training and evaluation of vision-language models (VLMs) for interpretable, scene-level understanding. We annotate 5,192 images drawn from Argoverse 1, Cityscapes, KITTI, and nuScenes using a 28-key category/sub-category knowledge base covering env...","url_abs":"https://arxiv.org/abs/2511.10701","url_pdf":"https://arxiv.org/pdf/2511.10701v2","authors":"[\"Yuankai He\",\"Weisong Shi\"]","published":"2025-11-12T21:13:19Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.RO\"]","methods":"[\"Language Model\",\"LoRA\"]","has_code":false,"code_links":[{"ID":607176,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2843015,"paper_url":"https://arxiv.org/abs/2511.10701","paper_title":"CARScenes: Semantic VLM Dataset for Safe Autonomous Driving","repo_url":"https://github.com/Croquembouche/CAR-Scenes","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}