基于时空因果推理的流式视频犯罪预测
Streaming Video Crime Anticipation with Spatio-Temporal Causal Reasoning
将实体间的隐式动态关系显式建模为时空因果超图，并以流式模块接入 VLM，为视频时序推理提供了一种可复用的因果结构注入方式，可用于任何需要预测未来事件或建模实体交互的视频理解任务。
原文依据 a streaming module that transforms implicit entity dynamics into explicit causal structures to enhance causal reasoning for crime in VLMs
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论犯罪预测能够支持主动的公共安全干预，然而现有的视频安防系统在很大程度上仍是被动的，无法检测犯罪的前兆。尽管当前基于视觉语言模型（VLM）的视频理解方法在高层推理方面展现出潜力，但它们并非为显式建模预测犯罪所必需的时空因果关系而设计。我们通过两个因果驱动的组件来解决这一局限。首先，我们构建了时空因果推理犯罪（STCRC）数据集，这是一个分层数据集，包含跨越五项渐进式因果推理任务的 73K 个样本，有助于犯罪前兆的学习。其次，我们提出了时空因果超图（STCH），这是一个流式模块，将隐式的实体动态转化为显式的因果结构，以增强 VLM 中对犯罪的因果推理。通过结合这两个组件，我们的框架推进了实时犯罪预测，在预测任务上取得提升：犯罪分类相对提升 70.7%，犯罪检测提升 10.1%，时序预测误差降低 3.7%。
英文原文摘要 1143 字符
Crime anticipation enables proactive public safety interventions, yet existing video security systems remain largely reactive, unable to detect precursors of crime. While current visual language models (VLM)-based video understanding methods show promise in high-level reasoning, they are not designed to explicitly model the spatio-temporal causal relationships essential for anticipating crimes. We address this limitation by two causal-driven components. First, we develop the Spatio-Temporal Causal Reasoning Crime (STCRC) dataset, a hierarchical dataset comprising 73K samples across five progressive causal reasoning tasks, facilitating criminal precursors learning. Second, we propose the Spatio-Temporal Causal Hypergraph (STCH), a streaming module that transforms implicit entity dynamics into explicit causal structures to enhance causal reasoning for crime in VLMs. By combining these two components, our framework advances real-time crime anticipation, achieving improvements in anticipatory tasks: a 70.7% relative improvement in crime classification, a 10.1% in crime detection, and a 3.7% reduction in temporal prediction error.