ReactVAU improves live video anomaly detection and explanation
ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding
Computer Vision and Pattern Recognition
Summary
Detecting unusual events in live video streams is tricky because many methods need to look at the whole video in advance, which isn’t possible in real time. The authors offer ReactVAU, a system that quickly spots potential anomalies using a simple detector, remembers important details without losing them, and only uses a slower, detailed analyzer when something suspicious happens. This approach helps understand strange events as they happen without slowing down processing. Their tests show ReactVAU works well on standard benchmarks and runs more efficiently than previous methods.
What this means in practice
- •For security monitoring teams: Monitor live surveillance video to detect and understand unusual behavior efficiently without delays caused by offline analysis.
- •For sports analysts: Analyze live sports footage to flag and describe rare or unexpected events quickly with minimal computational resources.
Authors
Chia-Hui Chen, Shih-Ying Yeh, Fu-En Yang, Min-Hung Chen, Shang-Hong Lai
Abstract
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/