A VideoMAE-v2 Approach to Zero-Shot Traffic Accident Anticipation

• URL: http://arxiv.org/abs/2606.09542v1
• Date: Mon, 08 Jun 2026 14:25:16 GMT
• Title: A VideoMAE-v2 Approach to Zero-Shot Traffic Accident Anticipation
• Abstract summary: We propose a framework that bridges the gap between the frame-level temporal risk estimation task and coarsely labelled binary accident datasets.<n>Our method achieves 2nd place in the 2026 CVPR@AUTOPILOT Zero-Shot Accident Anticipation competition.
• Score: 20.309082260025992
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Traffic accident anticipation -- predicting the likelihood of an imminent collision at every frame of a dashcam video -- is safety-critical yet difficult to scale, because collecting in-domain annotated accident footage for every deployment scenario is prohibitively expensive. We study this task under a zero-shot setting where no target-domain training data is available: the model must learn exclusively from a publicly available binary-labelled driving-accident dataset and generalise to unseen dashcam footage. We propose a framework that bridges the gap between the frame-level temporal risk estimation task and coarsely labelled binary accident datasets by coupling a VideoMAE-v2 backbone with a per-frame prediction head under a sliding-window protocol. Our method achieves 2nd place in the 2026 CVPR@AUTOPILOT Zero-Shot Accident Anticipation competition. Code is available at https://github.com/TimeSouth/zero-shot-taa-solution.

Related papers

• Zero-Shot Traffic Accident Detection via a Coarse-to-Fine VLM-Tracking Pipeline [0.10874100424278173]
  ACCIDENT @ CVPR benchmark evaluates exactly this joint prediction under a strict constraint.<n>We introduce a training-free, two-pass coarse-to-fine pipeline that pairs a frozen Qwen3-VL-32B-Instruct vision-language model with YOLO11x object detection and BoT-SORT tracking.<n>On the official 2,027-clip real-CCTV test set, our system achieves a three-way harmonic mean score of 0.504.
  arXiv  Detail & Related papers  (2026-08-09T19:08:56Z)
• 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)
• Accident Anticipation via Temporal Occurrence Prediction [15.813749445439292]
  Accident anticipation aims to predict potential collisions in an online manner, enabling timely alerts to enhance road safety.<n>Existing methods typically predict frame-level risk scores as indicators of hazard.<n>We propose a novel paradigm that shifts the prediction target from current-frame risk scoring to directly estimating accident scores at multiple future time steps.
  arXiv  Detail & Related papers  (2025-10-25T11:57:22Z)
• 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)
• DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving [76.29141888408265]
  We propose a large-scale dataset containing diverse accident scenarios that frequently occur in real-world driving. The proposed DeepAccident dataset includes 57K annotated frames and 285K annotated samples, approximately 7 times more than the large-scale nuScenes dataset.
  arXiv  Detail & Related papers  (2023-04-03T17:37:00Z)
• A Unified Framework for Event-based Frame Interpolation with Ad-hoc Deblurring in the Wild [72.0226493284814]
  We propose a unified framework for event-based frame that performs deblurring ad-hoc.<n>Our network consistently outperforms previous state-of-the-art methods on frame, single image deblurring, and the joint task of both.
  arXiv  Detail & Related papers  (2023-01-12T18:19:00Z)
• Augmenting Ego-Vehicle for Traffic Near-Miss and Accident Classification Dataset using Manipulating Conditional Style Translation [0.3441021278275805]
  There is no difference between accident and near-miss at the time before the accident happened. Our contribution is to redefine the accident definition and re-annotate the accident inconsistency on DADA-2000 dataset together with near-miss. The proposed method integrates two different components: conditional style translation (CST) and separable 3-dimensional convolutional neural network (S3D)
  arXiv  Detail & Related papers  (2023-01-06T22:04:47Z)
• 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)
• Object Rearrangement Using Learned Implicit Collision Functions [61.90305371998561]
  We propose a learned collision model that accepts scene and query object point clouds and predicts collisions for 6DOF object poses within the scene. We leverage the learned collision model as part of a model predictive path integral (MPPI) policy in a tabletop rearrangement task. The learned model outperforms both traditional pipelines and learned ablations by 9.8% in accuracy on a dataset of simulated collision queries.
  arXiv  Detail & Related papers  (2020-11-21T05:36:06Z)

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.