# ACCIDENT: A Benchmark Dataset for Vehicle Accident Detection from Traffic Surveillance Videos

arXiv: https://arxiv.org/abs/2604.09819 · HTML: https://mlsanity.com/paper/2604.09819/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 26 of 26)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication](https://mlsanity.com/paper/2109.07644/) (2021)
- [SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation](https://mlsanity.com/paper/2206.08367/) (2022)
- [A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction](https://mlsanity.com/paper/2108.06852/) (2021)
- [Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning](https://mlsanity.com/paper/2008.00334/) (2020)
- [DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving](https://mlsanity.com/paper/2304.01168/) (2023)
- [Unsupervised Traffic Accident Detection in First-Person Videos](https://mlsanity.com/paper/1903.00618/) (2019)
- [DADA-2000: Can Driving Accident be Predicted by Driver Attention? Analyzed by A Benchmark](https://mlsanity.com/paper/1904.12634/) (2019)
- [Synthetic Datasets for Autonomous Driving: A Survey](https://mlsanity.com/paper/2304.12205/) (2023)
- [DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation](https://mlsanity.com/paper/2107.10189/) (2021)
- [IDDA: a large-scale multi-domain dataset for autonomous driving](https://mlsanity.com/paper/2004.08298/) (2020)
- [Vision-Based Traffic Accident Detection and Anticipation: A Survey](https://mlsanity.com/paper/2308.15985/) (2023)
- [Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks](https://mlsanity.com/paper/1612.00390/) (2016)
- [When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis](https://mlsanity.com/paper/2501.10604/) (2025)
- [TAD: A Large-Scale Benchmark for Traffic Accidents Detection from Video Surveillance](https://mlsanity.com/paper/2209.12386/) (2022)
- [Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baseline](https://mlsanity.com/paper/2404.00847/) (2024)
- [TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning](https://mlsanity.com/paper/2404.09275/) (2024)
- [Zero-shot Hazard Identification in Autonomous Driving: A Case Study on the COOOL Benchmark](https://mlsanity.com/paper/2412.19944/) (2024)
- [Towards Vision Zero: The TUM Traffic Accid3nD Dataset](https://mlsanity.com/paper/2503.12095/) (2025)
- [Collision Detection: An Improved Deep Learning Approach Using SENet and ResNext](https://mlsanity.com/paper/2201.04766/) (2022)

## Built on by (most cited first, 7 of 7)

- [Zoom In, Reason Out: Efficient Far-field Anomaly Detection in Expressway Surveillance Videos via Focused VLM Reasoning Guided by Bayesian Inference](https://mlsanity.com/paper/2604.23724/) (2026)
- [Two-Pass Zero-Shot Temporal-Spatial Grounding of Rare Traffic Events in Surveillance Video](https://mlsanity.com/paper/2605.01512/) (2026)
- [Multi-Stage VLM Pipeline for Zero-Shot Traffic Accident Understanding](https://mlsanity.com/paper/2605.29325/) (2026)
- [Metadata-Aware Multi-Prompt Reasoning for Zero-Shot Accident Understanding](https://mlsanity.com/paper/2606.12047/) (2026)
- [Zero-Shot Traffic Accident Detection via a Coarse-to-Fine VLM-Tracking Pipeline](https://mlsanity.com/paper/2608.08867/) (2026)
- [SynCrash: A Multi-Stage Pipeline for Zero-Shot Accident Detection and Localization in Traffic Surveillance Video](https://mlsanity.com/paper/2608.29759/) (2026)
- [FPV-CRASH: A Dataset for Offline Crash Moment Localization in Drone First-Person-View Videos](https://mlsanity.com/paper/2610.19785/) (2026)

## Abstract (arXiv)

We introduce ACCIDENT, a benchmark dataset for traffic accident detection in CCTV footage, designed to evaluate models in supervised (IID and OOD) and zero-shot settings, reflecting both data-rich and data-scarce scenarios. The benchmark consists of a curated set of 2,027 real and 2,211 synthetic clips annotated with the accident time, spatial location, and high-level collision type. We define three core tasks: (i) temporal localization of the accident, (ii) its spatial localization, and (iii) collision type classification. Each task is evaluated using custom metrics that account for the uncertainty and ambiguity inherent in CCTV footage. In addition to the benchmark, we provide a diverse set of baselines, including heuristic, motion-aware, and vision-language approaches, and show that ACCIDENT is challenging. You can access the ACCIDENT at: https://accidentbench.github.io