Paper Detail
Chia-Hui Chen, Shih-Ying Yeh, Fu-En Yang, Min-Hung Chen, Shang-Hong Lai
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/
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{chen2026reactvau,
title = {ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding},
author = {Chia-Hui Chen and Shih-Ying Yeh and Fu-En Yang and Min-Hung Chen and Shang-Hong Lai},
year = {2026},
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 addres},
url = {https://huggingface.co/papers/2609.07941},
keywords = {Slow-Fast Decoupled Framework, Video Anomaly Understanding, Spatial Grid Folding, Anomaly-Aware Persistent Memory, MLLM, streaming video, causal reasoning, code available, huggingface daily},
eprint = {2609.07941},
archiveprefix = {arXiv},
}
{}