# RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipation

arXiv: https://arxiv.org/abs/2603.27165 · HTML: https://mlsanity.com/paper/2603.27165/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 44 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Builds on (most cited first, 30 of 30)

- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [Anticipative Video Transformer](https://mlsanity.com/paper/2106.02036/) (2021)
- [MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition](https://mlsanity.com/paper/2201.08383/) (2022)
- [Video Representation Learning by Dense Predictive Coding](https://mlsanity.com/paper/1909.04656/) (2019)
- [Temporal Cycle-Consistency Learning](https://mlsanity.com/paper/1904.07846/) (2019)
- [EGO-TOPO: Environment Affordances from Egocentric Video](https://mlsanity.com/paper/2001.04583/) (2020)
- [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)
- [DADA: Driver Attention Prediction in Driving Accident Scenarios](https://mlsanity.com/paper/1912.12148/) (2019)
- [DADA-2000: Can Driving Accident be Predicted by Driver Attention? Analyzed by A Benchmark](https://mlsanity.com/paper/1904.12634/) (2019)
- [Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB](https://mlsanity.com/paper/1804.02675/) (2018)
- [Abductive Ego-View Accident Video Understanding for Safe Driving Perception](https://mlsanity.com/paper/2403.00436/) (2024)
- [A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents](https://mlsanity.com/paper/2106.10197/) (2021)
- [Learning to Anticipate Egocentric Actions by Imagination](https://mlsanity.com/paper/2101.04924/) (2021)
- [Memory-and-Anticipation Transformer for Online Action Understanding](https://mlsanity.com/paper/2308.07893/) (2023)
- [Interaction Region Visual Transformer for Egocentric Action Anticipation](https://mlsanity.com/paper/2211.14154/) (2022)
- [Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors](https://mlsanity.com/paper/2306.12041/) (2023)
- [Knowledge Distillation for Action Anticipation via Label Smoothing](https://mlsanity.com/paper/2004.07711/) (2020)
- [VPTR: Efficient Transformers for Video Prediction](https://mlsanity.com/paper/2203.15836/) (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)
- [Improving Bird's Eye View Semantic Segmentation by Task Decomposition](https://mlsanity.com/paper/2404.01925/) (2024)
- [Real-time Accident Anticipation for Autonomous Driving Through Monocular Depth-Enhanced 3D Modeling](https://mlsanity.com/paper/2409.01256/) (2024)
- [Temporal Label Smoothing for Early Event Prediction](https://mlsanity.com/paper/2208.13764/) (2022)
- [Risk-Monotonicity in Statistical Learning](https://mlsanity.com/paper/2011.14126/) (2020)
- [Real-time Traffic Accident Anticipation with Feature Reuse](https://mlsanity.com/paper/2505.17449/) (2025)
- [Knowledge Distillation for Human Action Anticipation](https://mlsanity.com/paper/1904.04868/) (2019)
- [How to address monotonicity for model risk management?](https://mlsanity.com/paper/2305.00799/) (2023)
- [Accident Anticipation via Temporal Occurrence Prediction](https://mlsanity.com/paper/2510.22260/) (2025)

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

- [Comparison-Based Ordinal Learning for Proactive Driving Risk Assessment](https://mlsanity.com/paper/2607.11128/) (2026)
- [CoRE: Weakly Supervised Coarse-to-Fine Risk Evidence Learning in Driving Videos](https://mlsanity.com/paper/2608.25344/) (2026)

## Abstract (arXiv)

Accident anticipation aims to predict impending collisions from dashcam videos and trigger early alerts. Existing methods rely on binary supervision with manually annotated "anomaly onset" frames, which are subjective and inconsistent, leading to inaccurate risk estimation. In contrast, we propose RiskProp, a novel collision-anchored self-supervised risk propagation paradigm for early accident anticipation, which removes the need for anomaly onset annotations and leverages only the reliably annotated collision frame. RiskProp models temporal risk evolution through two observation-driven losses: first, since future frames contain more definitive evidence of an impending accident, we introduce a future-frame regularization loss that uses the model's next-frame prediction as a soft target to supervise the current frame, enabling backward propagation of risk signals; second, inspired by the empirical trend of rising risk before accidents, we design an adaptive monotonic constraint to encourage a non-decreasing progression over time. Experiments on CAP and Nexar demonstrate that RiskProp achieves state-of-the-art performance and produces smoother, more discriminative risk curves, improving both early anticipation and interpretability.