Khaled Waleed Dawoud, Muhammad Zaigham Zaheer, Khan Muhammad, Muhammad Haris Khan · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31478 · open-access PDF
视觉语言模型(VLMs)已经展示了视频异常检测的强大潜力,但密集的框架级推断使得它们无法实用的实时部署。现有的加速通常依赖于统一的采样,它忽略了内容动态,可以浪费静态细分的计算或错过本地化的异常。我们建议MoG-VLM是一个运动适应性异常检测框架,该框架纯粹利用运动作为轻量控制信号来决定什么时候需要VLM推断。
Machine translation (Meta M2M100); the English original follows.
Vision-Language Models (VLMs) have shown strong potential for video anomaly detection, but dense frame-level inference makes them impractical for real-time deployment. Existing acceleration commonly relies on uniform sampling, which ignores content dynamics and can either waste computation on static segments or miss localized anomalies. We propose MoG-VLM a motion-adaptive anomaly detection framework that leverages motion purely as a lightweight control signal to decide when VLM inference is necessary. To this end, we introduce Temporal Gradient Magnitude (TGM) which performs content-aware sam
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31478, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange