提出慢快分离框架，实现实时视频异常理解与高效推理。
ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding
- 快模块用空间网格折叠实时过滤异常，保持低延迟。
- 慢模块仅在可疑事件触发时启动，减少大模型调用次数。
- 适合需要实时响应的安防监控场景，兼顾精度与效率。
本文提出ReactVAU，一种面向实时流式视频异常理解（VAU）的慢快分离框架。现有方法依赖离线全局时间采样，违反因果性，无法用于实时监控；而通用流式模型虽满足因果性，却在内存压缩中稀释罕见瞬态异常，且长期无差别调用重型多模态大模型（MLLM）。ReactVAU通过三个协同组件解决此问题：基于空间网格折叠（SGF）的轻量级快检测模块，持续进行异常过滤；异常感知持久记忆（AAPM），防止关键视觉线索随时间衰减；仅在可疑事件触发时唤醒的重型慢推理模块，用于语义验证与因果描述。在多个基准测试上，ReactVAU在严格流式约束下同时实现优异的异常检测与因果推理性能，并显著降低计算开销，大幅减少重型MLLM调用频次。项目页面见https://huiyuiui.github.io/React_VAU/
原文摘要 · Abstract (English)
In this paper, we propose ReactVAU, a Slow-Fast Decoupled Framework for real-time streaming Video Anomaly Understanding (VAU). Existing VAU methods rely on offline inference with global temporal sampling, which violates causality and prevents deployment in live surveillance streams. Conversely, general streaming video models satisfy causal access but dilute rare transient anomalies during memory compression and often invoke heavyweight MLLMs uniformly over long normal intervals. React VAU addresses this gap with three synergistic components: a lightweight Fast Detection Module based on Spatial Grid Folding (SGF) for continuous anomaly filtering; an Anomaly-Aware Persistent Memory (AAPM) that protects critical visual cues from temporal decay; and a heavyweight Slow Reasoning Module that remains dormant during normal streams and is awakened only by suspicious events for semantic verification and causal description. Extensive experiments on multiple benchmarks demonstrate that ReactVAU operates under strict streaming constraints while simultaneously achieving competitive performance in both anomaly detection and causal reasoning, alongside significantly enhanced computational efficiency by minimizing heavyweight MLLM invocations. Project page is available at https://huiyuiui.github.io/React_VAU/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。