Metraipolis › archive › dc_7fa92c87cc68

CAViAR: A Causal Video Dataset for Fine-Grained Accident Reasoning in Real-World Scenarios — arXiv:2608.19380

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19380
License (as archived)
CC0-1.0
Archived
2026-10-18T12:04:32.344Z
SHA-256 of the archived text
aa6611fa75a97d9c2b47e75713781c7af4a4077341111dba02358127fa75cf48
Stable URL of this page
https://metraipolis.com/documento/dc_7fa92c87cc68

How to cite

CAViAR: A Causal Video Dataset for Fine-Grained Accident Reasoning in Real-World Scenarios — arXiv:2608.19380 — arXiv (en), https://arxiv.org/abs/2608.19380 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7fa92c87cc68 (Metraipolis archive dc_7fa92c87cc68, sha256 aa6611fa75a97d9c2b47e75713781c7af4a4077341111dba02358127fa75cf48)
BibTeX
@misc{dc7fa92c87cc68,
  title = {CAViAR: A Causal Video Dataset for Fine-Grained Accident Reasoning in Real-World Scenarios — arXiv:2608.19380},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19380},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7fa92c87cc68; sha256 aa6611fa75a97d9c2b47e75713781c7af4a4077341111dba02358127fa75cf48},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19380. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While modern autonomous driving systems excel at perception tasks such as object detection and trajectory prediction, they lack the high-level causal reasoning required to interpret traffic accidents. In particular, determining responsibility, such as identifying who is at fault and which traffic rule was violated, remains largely unexplored in current benchmarks. To this end, we introduce CAViAR (Causal Accident Video and Incident Analysis Repository), a human-annotated dashcam benchmark comprising 2,249 real-world accident videos collected from CarCrashDataset (CCD) and Nexar. Each video is annotated with structured labels spanning environmental conditions, accident type, causal explanation, apparent At-Fault Agent, affected agent, and apparent rule-violation category. We benchmark state-of-the-art vision-language models (VLMs), including Cosmos-Reason2, Qwen3-VL, and InternVL3. Once class imbalance is accounted for with majority/random baselines and balanced metrics, perceptual competence is uneven--lighting is nearly solved, whereas weather and road-condition accuracy fall at or below the majority-class baseline---and all models degrade sharply on accident type and responsibility reasoning. Overall, CAViAR exposes a practical Perception--Reasoning Gap: current VLMs may recognize salient context, but do not reliably map visible agent actions to annotated rule-relevant responsibility categories in safety-critical driving scenarios. Code, annotation schema, prompts, and evaluation scripts are available at: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.19380 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T12:01:57.687Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).