# A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents

arXiv: https://arxiv.org/abs/2106.10197 · HTML: https://mlsanity.com/paper/2106.10197/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 18 Jun 2021.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Deep Learning for Anomaly Detection: A Survey](https://mlsanity.com/paper/1901.03407/) (2019)
- [Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art](https://mlsanity.com/paper/1704.05519/) (2017)
- [Peeking into the Future: Predicting Future Person Activities and Locations in Videos](https://mlsanity.com/paper/1902.03748/) (2019)
- [Accelerating Very Deep Convolutional Networks for Classification and Detection](https://mlsanity.com/paper/1505.06798/) (2015)
- [Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning](https://mlsanity.com/paper/2008.00334/) (2020)
- [Quasi-Recurrent Neural Networks](https://mlsanity.com/paper/1611.01576/) (2016)
- [Temporal Recurrent Networks for Online Action Detection](https://mlsanity.com/paper/1811.07391/) (2018)
- [Unsupervised Traffic Accident Detection in First-Person Videos](https://mlsanity.com/paper/1903.00618/) (2019)
- [Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB](https://mlsanity.com/paper/1804.02675/) (2018)
- [Encouraging LSTMs to Anticipate Actions Very Early](https://mlsanity.com/paper/1703.07023/) (2017)
- [Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization](https://mlsanity.com/paper/1705.06560/) (2017)
- [Pedestrian Path, Pose and Intention Prediction through Gaussian Process Dynamical Models and Pedestrian Activity Recognition](https://mlsanity.com/paper/2004.14747/) (2020)
- [Global Feature Aggregation for Accident Anticipation](https://mlsanity.com/paper/2006.08942/) (2020)

## Built on by (most cited first, 30 of 42)

- [Abductive Ego-View Accident Video Understanding for Safe Driving Perception](https://mlsanity.com/paper/2403.00436/) (2024)
- [Vision-Based Traffic Accident Detection and Anticipation: A Survey](https://mlsanity.com/paper/2308.15985/) (2023)
- [Behavioral Intention Prediction in Driving Scenes: A Survey](https://mlsanity.com/paper/2211.00385/) (2022)
- [Nexar Dashcam Collision Prediction Dataset and Challenge](https://mlsanity.com/paper/2503.03848/) (2025)
- [TAD: A Large-Scale Benchmark for Traffic Accidents Detection from Video Surveillance](https://mlsanity.com/paper/2209.12386/) (2022)
- [Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmark](https://mlsanity.com/paper/2212.09381/) (2022)
- [CRASH: Crash Recognition and Anticipation System Harnessing with Context-Aware and Temporal Focus Attentions](https://mlsanity.com/paper/2407.17757/) (2024)
- [Real-time Accident Anticipation for Autonomous Driving Through Monocular Depth-Enhanced 3D Modeling](https://mlsanity.com/paper/2409.01256/) (2024)
- [FBLNet: FeedBack Loop Network for Driver Attention Prediction](https://mlsanity.com/paper/2212.02096/) (2022)
- [Real-time Traffic Accident Anticipation with Feature Reuse](https://mlsanity.com/paper/2505.17449/) (2025)
- [World Model-Based End-to-End Scene Generation for Accident Anticipation in Autonomous Driving](https://mlsanity.com/paper/2507.12762/) (2025)
- [Towards explainable artificial intelligence (XAI) for early anticipation of traffic accidents](https://mlsanity.com/paper/2108.00273/) (2021)
- [Domain-Enhanced Dual-Branch Model for Efficient and Interpretable Accident Anticipation](https://mlsanity.com/paper/2507.12755/) (2025)
- [An Attention-guided Multistream Feature Fusion Network for Localization of Risky Objects in Driving Videos](https://mlsanity.com/paper/2209.07922/) (2022)
- [Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction](https://mlsanity.com/paper/2310.04671/) (2023)
- [When, Where, and What? A Novel Benchmark for Accident Anticipation and Localization with Large Language Models](https://mlsanity.com/paper/2407.16277/) (2024)
- [BADAS: Context Aware Collision Prediction Using Real-World Dashcam Data](https://mlsanity.com/paper/2510.14876/) (2025)
- [Accident Anticipation via Temporal Occurrence Prediction](https://mlsanity.com/paper/2510.22260/) (2025)
- [Safety in Traffic Management Systems: A Comprehensive Survey](https://mlsanity.com/paper/2308.06204/) (2023)
- [When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network](https://mlsanity.com/paper/2506.17457/) (2025)
- [PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning](https://mlsanity.com/paper/2606.02443/) (2026)
- [Reinforcement Learning for Predicting Traffic Accidents](https://mlsanity.com/paper/2212.04677/) (2022)
- [EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis](https://mlsanity.com/paper/2506.10002/) (2025)
- [RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipation](https://mlsanity.com/paper/2603.27165/) (2026)
- [Deep Learning Advances in Vision-Based Traffic Accident Anticipation: A Comprehensive Review of Methods, Datasets, and Future Directions](https://mlsanity.com/paper/2505.07611/) (2025)
- [STAGNet: A Spatio-Temporal Graph and LSTM Framework for Accident Anticipation](https://mlsanity.com/paper/2508.15216/) (2025)
- [DriverGaze360: OmniDirectional Driver Attention with Object-Level Guidance](https://mlsanity.com/paper/2512.14266/) (2025)
- [Beyond the Beep: Scalable Collision Anticipation and Real-Time Explainability with BADAS-2.0](https://mlsanity.com/paper/2604.05767/) (2026)
- [VAGNet: Vision-based Accident Anticipation with Global Features](https://mlsanity.com/paper/2604.09305/) (2026)
- [A VideoMAE-v2 Approach to Zero-Shot Traffic Accident Anticipation](https://mlsanity.com/paper/2606.09542/) (2026)

## Abstract (arXiv)

The rapid advancement of sensor technologies and artificial intelligence are creating new opportunities for traffic safety enhancement. Dashboard cameras (dashcams) have been widely deployed on both human driving vehicles and automated driving vehicles. A computational intelligence model that can accurately and promptly predict accidents from the dashcam video will enhance the preparedness for accident prevention. The spatial-temporal interaction of traffic agents is complex. Visual cues for predicting a future accident are embedded deeply in dashcam video data. Therefore, the early anticipation of traffic accidents remains a challenge. Inspired by the attention behavior of humans in visually perceiving accident risks, this paper proposes a Dynamic Spatial-Temporal Attention (DSTA) network for the early accident anticipation from dashcam videos. The DSTA-network learns to select discriminative temporal segments of a video sequence with a Dynamic Temporal Attention (DTA) module. It also learns to focus on the informative spatial regions of frames with a Dynamic Spatial Attention (DSA) module. A Gated Recurrent Unit (GRU) is trained jointly with the attention modules to predict the probability of a future accident. The evaluation of the DSTA-network on two benchmark datasets confirms that it has exceeded the state-of-the-art performance. A thorough ablation study that assesses the DSTA-network at the component level reveals how the network achieves such performance. Furthermore, this paper proposes a method to fuse the prediction scores from two complementary models and verifies its effectiveness in further boosting the performance of early accident anticipation.