RiskProp：碰撞锚定的自监督风险传播用于早期事故预测
RiskProp: Collision-Anchored Self-Supervised Risk Propagation For Early Accident Anticipation
提出碰撞锚定的自监督风险传播范式，用未来帧预测作为软目标监督当前帧，并设计自适应单调约束，可复用于其他需要早期预警的时序视频任务（如异常检测、动作预测）。
原文依据 we propose RiskProp, a novel collision-anchored self-supervised risk propagation paradigm for early accident anticipation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论事故预测旨在从行车记录仪视频中预测即将发生的碰撞并触发早期警报。现有方法依赖二元监督和人工标注的“异常起始”帧，这些标注主观且不一致，导致风险估计不准确。相比之下，我们提出RiskProp，一种新颖的碰撞锚定的自监督风险传播范式，用于早期事故预测，它无需异常起始标注，仅利用可靠标注的碰撞帧。RiskProp通过两个观测驱动的损失来建模时序风险演化。首先，由于未来帧包含更明确的即将发生事故的证据，我们引入未来帧正则化损失，使用模型的下一帧预测作为软目标来监督当前帧，从而实现风险信号的反向传播。其次，受事故前风险上升的经验趋势启发，我们设计了一种自适应单调约束，以鼓励风险随时间非递减地演进。在CAP-DATA和Nexar上的实验表明，RiskProp达到了最优性能，并产生更平滑、更具判别力的风险曲线，同时提升了早期预测能力和可解释性。
英文原文摘要 1254 字符
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-DATA and Nexar demonstrate that RiskProp achieves state-of-the-art performance and produces smoother, more discriminative risk curves, improving both early anticipation and interpretability.