# FLaRA: Predicting Future Latent Representations for Accident Anticipation

arXiv: https://arxiv.org/abs/2606.14380 · HTML: https://mlsanity.com/paper/2606.14380/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 12 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning](https://mlsanity.com/paper/2008.00334/) (2020)
- [DADA-2000: Can Driving Accident be Predicted by Driver Attention? Analyzed by A Benchmark](https://mlsanity.com/paper/1904.12634/) (2019)
- [A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents](https://mlsanity.com/paper/2106.10197/) (2021)
- [Predicting the Future: A Jointly Learnt Model for Action Anticipation](https://mlsanity.com/paper/1912.07148/) (2019)
- [Spatio-Temporal Scene-Graph Embedding for Autonomous Vehicle Collision Prediction](https://mlsanity.com/paper/2111.06123/) (2021)
- [Nexar Dashcam Collision Prediction Dataset and Challenge](https://mlsanity.com/paper/2503.03848/) (2025)
- [Towards Anomaly Detection in Dashcam Videos](https://mlsanity.com/paper/2004.05261/) (2020)
- [Real-time Accident Anticipation for Autonomous Driving Through Monocular Depth-Enhanced 3D Modeling](https://mlsanity.com/paper/2409.01256/) (2024)
- [BADAS: Context Aware Collision Prediction Using Real-World Dashcam Data](https://mlsanity.com/paper/2510.14876/) (2025)

## Abstract (arXiv)

Anticipating traffic accidents from dashcam videos is a critical challenge in intelligent transportation systems. Existing methods typically map visual context directly to a collision probability without explicitly modeling the future evolution of the driving scene. In this paper we propose FLaRA (Predicting Future Latent Representations for Accident Anticipation), a novel predictive architecture that shifts this paradigm by forecasting future latent representations for accident anticipation. Building upon the Video Joint-Embedding Predictive Architecture (V-JEPA2), our model conditions a predictor network on observed context frames to predict the forthcoming latent features of the scene. A classifier then operates on these predicted future representations rather than only on past observations. To ensure these forecasts remain grounded in realistic future dynamics, we introduce a joint training objective that simultaneously optimizes an auxiliary feature-level reconstruction loss and a cross-entropy classification loss. Extensive evaluations on the Nexar dataset, alongside cross-domain validations on the DAD, DADA-2000, and DoTA benchmarks, demonstrate that our approach achieves state-of-the-art performance while maintaining realistic early warning capabilities.