# CARA: Concept-Aware Risk Attention for Interpretable Collision Anticipation

arXiv: https://arxiv.org/abs/2607.22494 · HTML: https://mlsanity.com/paper/2607.22494/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 46 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [GPT-Driver: Learning to Drive with GPT](https://mlsanity.com/paper/2310.01415/) (2023)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning](https://mlsanity.com/paper/2008.00334/) (2020)
- [Unsupervised Traffic Accident Detection in First-Person Videos](https://mlsanity.com/paper/1903.00618/) (2019)
- [A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents](https://mlsanity.com/paper/2106.10197/) (2021)
- [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)
- [GraphOracle: Efficient Fully-Inductive Knowledge Graph Reasoning via Relation-Dependency Graphs](https://mlsanity.com/paper/2505.11125/) (2025)
- [Domain-Enhanced Dual-Branch Model for Efficient and Interpretable Accident Anticipation](https://mlsanity.com/paper/2507.12755/) (2025)
- [Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning](https://mlsanity.com/paper/2507.20498/) (2025)
- [Eyes on the Road, Mind Beyond Vision: Context-Aware Multi-modal Enhanced Risk Anticipation](https://mlsanity.com/paper/2507.06444/) (2025)

## Abstract (arXiv)

Collision anticipation in autonomous driving requires not only accurate early warnings but also interpretable reasoning about what risk factors are being tracked and how risk evolves over time. Existing methods fall short in this regard: feature-driven models are opaque, post-hoc explanations often lack fidelity, and concept-based methods are mostly designed for static recognition rather than dynamic driving scenes. We propose CARA (Concept-Aware Risk Attention), an intrinsically interpretable spatio-temporal framework for collision anticipation. CARA derives domain-grounded risk concepts from accident narratives, aligns them with video frames via vision-language similarity, and organizes them into evolving concept trajectories. These trajectories provide explicit risk evidence that guides spatial attention, temporal attention, and anticipation, allowing semantic concepts to directly influence both where the model attends and how it predicts risk over time. By treating semantic risk factors as dynamic intermediate evidence rather than auxiliary post-hoc explanations, CARA tightly couples interpretability with the predictive process. Extensive experiments on three benchmarks show that CARA consistently improves anticipation accuracy and warning earliness over strong baselines, while providing sparse and semantically grounded concept evidence.