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

• URL: http://arxiv.org/abs/2608.19380v1
• Date: Wed, 19 Aug 2026 18:51:21 GMT
• Title: CAViAR: A Causal Video Dataset for Fine-Grained Accident Reasoning in Real-World Scenarios
• Abstract summary: We introduce CAViAR (Causal Accident Video and Incident Analysis Repository), a human-annotated dashcam benchmark comprising 2,249 real-world accident videos.<n>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.<n>We benchmark state-of-the-art vision-language models (VLMs), including Cosmos-Reason2, Qwen3-VL, and InternVL3.
• Score: 10.195587813770075
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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: https://github.com/nec-labs-ma/CAViAR

Related papers

• AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding [12.229867730747996]
  We present AUTOPILOT-VQA, an incident-centric visual question answering benchmark for dashcam video understanding.<n>The dataset evaluates different systems through structured questions designed around real-world driving incidents and near-incidents.<n>Our benchmark support developments for more interpretable, robust, and safety-conscious vision-language systems for real-world autonomous driving.
  arXiv  Detail & Related papers  (2026-07-09T17:46:24Z)
• Learning Responsibility-Attributed Adversarial Scenarios for Testing Autonomous Vehicles [14.04593970867671]
  CARS (Context-Aware, Responsibility-attributed Scenario generation) is a framework that integrates responsibility attribution directly into adversarial scenario generation.<n> CARS consistently discovers feasible collision scenarios with high attribution rates under regulation-prescribed careful and competent driver models.
  arXiv  Detail & Related papers  (2026-05-13T16:33:07Z)
• ACCIDENT: A Benchmark Dataset for Vehicle Accident Detection from Traffic Surveillance Videos [0.0]
  ACCIDENT is a benchmark dataset for traffic accident detection in CCTV footage.<n>It is designed to evaluate models in supervised (IID and OOD) and zero-shot settings.
  arXiv  Detail & Related papers  (2026-04-10T18:51:19Z)
• CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning [27.23760411917563]
  We present textbfCrashSight, a vision-language benchmark for roadway crash understanding using real-world roadside camera data.<n>The dataset comprises 250 crash videos, annotated with 13K multiple-choice question-answer pairs organized under a two-tier taxonomy.<n>We benchmark 8 state-of-the-art VLMs and show that, despite strong scene description capabilities, current models struggle with temporal and causal reasoning in safety-critical scenarios.
  arXiv  Detail & Related papers  (2026-04-09T16:52:04Z)
• Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning [71.19675094463834]
  This work introduces Counterfactual VLA, a self-reflective VLA framework that enables the model to reason about and revise its planned actions before execution.<n>CF-VLA first generates time-segmented meta-actions that summarize driving intent, and then performs counterfactual reasoning conditioned on both the meta-actions and the visual context.<n> Experiments on large-scale driving datasets show that CF-VLA improves trajectory accuracy by up to 17.6%, enhances safety metrics by 20.5%, and exhibits adaptive thinking.
  arXiv  Detail & Related papers  (2025-12-30T19:04:17Z)
• AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond [101.20320617562321]
  AccidentBench is a large-scale benchmark that combines vehicle accident scenarios with Beyond domains.<n>The benchmark contains approximately 2000 videos and over 19000 human-annotated question-answer pairs.
  arXiv  Detail & Related papers  (2025-09-30T17:59:13Z)
• Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving [55.96227460521096]
  Vision-Language Models (VLMs) have been integrated into autonomous driving systems to enhance reasoning capabilities.<n>We propose a natural reflection-based backdoor attack targeting VLM systems in autonomous driving scenarios.<n>Our findings uncover a new class of attacks that exploit the stringent real-time requirements of autonomous driving.
  arXiv  Detail & Related papers  (2025-05-09T20:28:17Z)
• EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis [79.25588905883191]
  Traffic Accident Anticipation (TAA) in traffic scenes is a challenging problem for achieving zero fatalities in the future.<n>We propose an Attentive Video Diffusion (AVD) model that synthesizes additional accident video clips.
  arXiv  Detail & Related papers  (2025-03-16T01:56:38Z)
• Abductive Ego-View Accident Video Understanding for Safe Driving Perception [75.60000661664556]
  We present MM-AU, a novel dataset for Multi-Modal Accident video Understanding. MM-AU contains 11,727 in-the-wild ego-view accident videos, each with temporally aligned text descriptions. We present an Abductive accident Video understanding framework for Safe Driving perception (AdVersa-SD)
  arXiv  Detail & Related papers  (2024-03-01T10:42:52Z)
• Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmark [77.54411007883962]
  We propose a Cognitive Accident Prediction (CAP) method that explicitly leverages human-inspired cognition of text description on the visual observation and the driver attention to facilitate model training. CAP is formulated by an attentive text-to-vision shift fusion module, an attentive scene context transfer module, and the driver attention guided accident prediction module. We construct a new large-scale benchmark consisting of 11,727 in-the-wild accident videos with over 2.19 million frames.
  arXiv  Detail & Related papers  (2022-12-19T11:43:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.