# Cerberus: Real-Time Video Anomaly Detection via Cascaded Vision-Language Models

arXiv: https://arxiv.org/abs/2510.16290 · HTML: https://mlsanity.com/paper/2510.16290/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 27 of its 51 references that are in the map.
- First posted on arXiv 18 Oct 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections](https://mlsanity.com/paper/2205.12005/) (2022)
- [A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction](https://mlsanity.com/paper/2108.06852/) (2021)
- [A Review on Edge Large Language Models: Design, Execution, and Applications](https://mlsanity.com/paper/2410.11845/) (2024)
- [A Survey of Single-Scene Video Anomaly Detection](https://mlsanity.com/paper/2004.05993/) (2020)
- [Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding](https://mlsanity.com/paper/2310.05424/) (2023)
- [VideoVista: A Versatile Benchmark for Video Understanding and Reasoning](https://mlsanity.com/paper/2406.11303/) (2024)
- [GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection](https://mlsanity.com/paper/1908.05884/) (2019)
- [Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers](https://mlsanity.com/paper/2012.10557/) (2020)
- [Hawk: Learning to Understand Open-World Video Anomalies](https://mlsanity.com/paper/2405.16886/) (2024)
- [Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction](https://mlsanity.com/paper/2011.02763/) (2020)
- [A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation](https://mlsanity.com/paper/2305.13611/) (2023)
- [Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts](https://mlsanity.com/paper/2408.05905/) (2024)
- [Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection](https://mlsanity.com/paper/2404.09654/) (2024)
- [A Vision-based System for Traffic Anomaly Detection using Deep Learning and Decision Trees](https://mlsanity.com/paper/2104.06856/) (2021)
- [An Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Prediction](https://mlsanity.com/paper/2406.15395/) (2024)
- [Sherlock: Towards Multi-scene Video Abnormal Event Extraction and Localization via a Global-local Spatial-sensitive LLM](https://mlsanity.com/paper/2502.18863/) (2025)
- [AVA: Towards Agentic Video Analytics with Vision Language Models](https://mlsanity.com/paper/2505.00254/) (2025)

## Built on by (most cited first, 1 of 1)

- [NOVA: Normal-Side Modeling for Training-Free Zero-Shot Video Anomaly Detection](https://mlsanity.com/paper/2609.06360/) (2026)

## Abstract (arXiv)

Video anomaly detection (VAD) has rapidly advanced by recent development of Vision-Language Models (VLMs). While these models offer superior zero-shot detection capabilities, their immense computational cost and unstable visual grounding performance hinder real-time deployment. To overcome these challenges, we introduce Cerberus, a two-stage cascaded system designed for efficient yet accurate real-time VAD. Cerberus learns normal behavioral rules offline, and combines lightweight filtering with fine-grained VLM reasoning during online inference. The performance gains of Cerberus come from two key innovations: motion mask prompting and rule-based deviation detection. The former directs the VLM's attention to regions relevant to motion, while the latter identifies anomalies as deviations from learned norms rather than enumerating possible anomalies. Extensive evaluations on four datasets show that Cerberus on average achieves 57.68 fps on an NVIDIA L40S GPU, a 151.79× speedup, and 97.2% accuracy comparable to the state-of-the-art VLM-based VAD methods, establishing it as a practical solution for real-time video analytics.