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

arXiv: https://arxiv.org/abs/2606.09542 · HTML: https://mlsanity.com/paper/2606.09542/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Builds on (most cited first, 17 of 17)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning](https://mlsanity.com/paper/2008.00334/) (2020)
- [DADA: Driver Attention Prediction in Driving Accident Scenarios](https://mlsanity.com/paper/1912.12148/) (2019)
- [A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents](https://mlsanity.com/paper/2106.10197/) (2021)
- [T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving](https://mlsanity.com/paper/2411.18894/) (2024)
- [Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature](https://mlsanity.com/paper/2303.12332/) (2023)
- [Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression](https://mlsanity.com/paper/2501.03674/) (2025)
- [Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning](https://mlsanity.com/paper/2502.12425/) (2025)
- [Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embedding](https://mlsanity.com/paper/2303.09706/) (2023)
- [RGB-Depth Fusion GAN for Indoor Depth Completion](https://mlsanity.com/paper/2203.10856/) (2022)
- [DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency](https://mlsanity.com/paper/2504.12080/) (2025)
- [SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.21585/) (2025)
- [Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoning](https://mlsanity.com/paper/2512.15153/) (2025)
- [Towards Balanced Multi-Modal Learning in 3D Human Pose Estimation](https://mlsanity.com/paper/2501.05264/) (2025)
- [RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion](https://mlsanity.com/paper/2306.03584/) (2023)

## Built on by (most cited first, 1 of 1)

- [Investigating Spatiotemporal Redundancy in Video Transformer for Collision Anticipation](https://mlsanity.com/paper/2610.04727/) (2026)

## Abstract (arXiv)

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.