# MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection

arXiv: https://arxiv.org/abs/2510.21449 · HTML: https://mlsanity.com/paper/2510.21449/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 24 Oct 2025.

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [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)
- [MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection](https://mlsanity.com/paper/2104.01633/) (2021)
- [A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction](https://mlsanity.com/paper/2108.06852/) (2021)
- [Generative Cooperative Learning for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2203.03962/) (2022)
- [MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2211.15098/) (2022)
- [Harnessing Large Language Models for Training-free Video Anomaly Detection](https://mlsanity.com/paper/2404.01014/) (2024)
- [Streaming Dense Video Captioning](https://mlsanity.com/paper/2404.01297/) (2024)
- [Learning Normal Dynamics in Videos with Meta Prototype Network](https://mlsanity.com/paper/2104.06689/) (2021)
- [CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2212.05136/) (2022)
- [GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection](https://mlsanity.com/paper/1908.05884/) (2019)
- [EventVAD: Training-Free Event-Aware Video Anomaly Detection](https://mlsanity.com/paper/2504.13092/) (2025)
- [A Vision-based System for Traffic Anomaly Detection using Deep Learning and Decision Trees](https://mlsanity.com/paper/2104.06856/) (2021)
- [DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Network](https://mlsanity.com/paper/2211.00882/) (2022)
- [Online Anomaly Detection in Surveillance Videos with Asymptotic Bounds on False Alarm Rate](https://mlsanity.com/paper/2010.07110/) (2020)
- [Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations](https://mlsanity.com/paper/2307.01533/) (2023)
- [Survey on video anomaly detection in dynamic scenes with moving cameras](https://mlsanity.com/paper/2308.07050/) (2023)
- [Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning](https://mlsanity.com/paper/2412.12791/) (2024)
- [Memory-augmented Online Video Anomaly Detection](https://mlsanity.com/paper/2302.10719/) (2023)

## Built on by (most cited first, 11 of 11)

- [Phase-Aware Mixture of Experts for Agentic Reinforcement Learning](https://mlsanity.com/paper/2602.17038/) (2026)
- [TAU-R1: Visual Language Model for Traffic Anomaly Understanding](https://mlsanity.com/paper/2603.19098/) (2026)
- [Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models](https://mlsanity.com/paper/2605.12725/) (2026)
- [Reinforcement Learning Enhanced LLM Agents for Complex Vehicle Routing Problems](https://mlsanity.com/paper/2609.00859/) (2026)
- [Explainable Forensics of Manipulated Segments in Untrimmed Long Videos](https://mlsanity.com/paper/2606.02402/) (2026)
- [Look Inside Each Video: Rethinking How Video Anomaly Detection Is Evaluated](https://mlsanity.com/paper/2608.21854/) (2026)
- [ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding](https://mlsanity.com/paper/2609.07941/) (2026)
- [RoboVAD: A Large Cross-Domain Evaluation Benchmark for Anomaly Detection in Robotic Arm Manipulation Videos](https://mlsanity.com/paper/2609.17843/) (2026)
- [PARSEE-VAD: Efficient Training-Free Online Video Anomaly Detection via Proposition-Aware Reasoning and Streaming Evidence Escalation](https://mlsanity.com/paper/2609.33236/) (2026)
- [Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding](https://mlsanity.com/paper/2610.01754/) (2026)
- [DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding](https://mlsanity.com/paper/2610.19849/) (2026)

## Abstract (arXiv)

Video Anomaly Detection (VAD) aims to locate unusual activities or behaviors within videos. Recently, offline VAD has garnered substantial research attention, which has been invigorated by the progress in large language models (LLMs) and vision-language models (VLMs), offering the potential for a more nuanced understanding of anomalies. However, online VAD has seldom received attention due to real-time constraints and computational intensity. In this paper, we introduce a novel Memory-based online scoring queue scheme for Training-free VAD (MoniTor), to address the inherent complexities in online VAD. Specifically, MoniTor applies a streaming input to VLMs, leveraging the capabilities of pre-trained large-scale models. To capture temporal dependencies more effectively, we incorporate a novel prediction mechanism inspired by Long Short-Term Memory (LSTM) networks. This ensures the model can effectively model past states and leverage previous predictions to identify anomalous behaviors. Thereby, it better understands the current frame. Moreover, we design a scoring queue and an anomaly prior to dynamically store recent scores and cover all anomalies in the monitoring scenario, providing guidance for LLMs to distinguish between normal and abnormal behaviors over time. We evaluate MoniTor on two large datasets (i.e., UCF-Crime and XD-Violence) containing various surveillance and real-world scenarios. The results demonstrate that MoniTor outperforms state-of-the-art methods and is competitive with weakly supervised methods without training. Code is available at https://github.com/YsTvT/MoniTor.