# A Modular Zero-Shot Pipeline for Accident Detection, Localization, and Classification in Traffic Surveillance Video

arXiv: https://arxiv.org/abs/2604.09685 · HTML: https://mlsanity.com/paper/2604.09685/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 5 Apr 2026.

## Builds on (most cited first, 5 of 5)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)

## Built on by (most cited first, 2 of 2)

- [Two-Pass Zero-Shot Temporal-Spatial Grounding of Rare Traffic Events in Surveillance Video](https://mlsanity.com/paper/2605.01512/) (2026)
- [Frame-Synchronous Hand Gesture Detection by Projected Winding Order](https://mlsanity.com/paper/2609.13269/) (2026)

## Abstract (arXiv)

We describe a zero-shot pipeline developed for the ACCIDENT @ CVPR 2026 challenge. The challenge requires predicting when, where, and what type of traffic accident occurs in surveillance video, without labeled real-world training data. Our method separates the problem into three independent modules. The first module localizes the collision in time by running peak detection on z-score normalized frame-difference signals. The second module finds the impact location by computing the weighted centroid of cumulative dense optical flow magnitude maps using the Farneback algorithm. The third module classifies collision type by measuring cosine similarity between CLIP image embeddings of frames near the detected peak and text embeddings built from multi-prompt natural language descriptions of each collision category. No domain-specific fine-tuning is involved; the pipeline processes each video using only pre-trained model weights. Our implementation is publicly available as a Kaggle notebook.