# VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding

arXiv: https://arxiv.org/abs/2507.21507 · HTML: https://mlsanity.com/paper/2507.21507/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 42 references that are in the map.
- First posted on arXiv 29 Jul 2025.

## Builds on (most cited first, 30 of 32)

- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding](https://mlsanity.com/paper/2409.14485/) (2024)
- [A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction](https://mlsanity.com/paper/2108.06852/) (2021)
- [VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2308.11681/) (2023)
- [Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection](https://mlsanity.com/paper/2203.14506/) (2022)
- [Generative Cooperative Learning for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2203.03962/) (2022)
- [UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection](https://mlsanity.com/paper/2111.08644/) (2021)
- [Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers](https://mlsanity.com/paper/2305.07011/) (2023)
- [Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2302.05160/) (2023)
- [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)
- [Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM](https://mlsanity.com/paper/2406.12235/) (2024)
- [Few-shot Scene-adaptive Anomaly Detection](https://mlsanity.com/paper/2007.07843/) (2020)
- [Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles](https://mlsanity.com/paper/2207.10172/) (2022)
- [Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models](https://mlsanity.com/paper/2407.10299/) (2024)
- [Hawk: Learning to Understand Open-World Video Anomalies](https://mlsanity.com/paper/2405.16886/) (2024)
- [Video Anomaly Detection and Explanation via Large Language Models](https://mlsanity.com/paper/2401.05702/) (2024)
- [Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly](https://mlsanity.com/paper/2405.00181/) (2024)
- [Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection](https://mlsanity.com/paper/2110.09768/) (2021)
- [Towards Open Set Video Anomaly Detection](https://mlsanity.com/paper/2208.11113/) (2022)
- [Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection](https://mlsanity.com/paper/2310.12790/) (2023)
- [VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models](https://mlsanity.com/paper/2412.01095/) (2024)
- [VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs](https://mlsanity.com/paper/2406.10326/) (2024)
- [FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation](https://mlsanity.com/paper/2106.08613/) (2021)
- [AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM](https://mlsanity.com/paper/2503.04504/) (2025)

## Built on by (most cited first, 8 of 8)

- [U2UData+: A Scalable Swarm UAVs Autonomous Flight Dataset for Embodied Long-horizon Tasks](https://mlsanity.com/paper/2509.00055/) (2025)
- [ALARM: Automated MLLM-Based Anomaly Detection in Complex-EnviRonment Monitoring with Uncertainty Quantification](https://mlsanity.com/paper/2512.03101/) (2025)
- [Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models](https://mlsanity.com/paper/2605.02912/) (2026)
- [TAU-Bench: From Anomaly Instance Tracking to Fine-Grained Video Anomaly Understanding](https://mlsanity.com/paper/2608.05699/) (2026)
- [Advancing Adaptive Multi-Stage Video Anomaly Reasoning: A Benchmark Dataset and Method](https://mlsanity.com/paper/2601.10165/) (2026)
- [LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation](https://mlsanity.com/paper/2604.19167/) (2026)
- [Learning Temporal Evidence Selection for Video Anomaly Understanding](https://mlsanity.com/paper/2610.16299/) (2026)
- [Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis](https://mlsanity.com/paper/2610.16324/) (2026)

## Abstract (arXiv)

Video Anomaly Detection (VAD) aims to identify anomalous events in videos and accurately determine their time intervals. Current VAD methods mainly fall into two categories: traditional DNN-based approaches that focus on temporal localization, and LLM-based approaches that emphasize semantic understanding. Both anomaly understanding and grounding are essential for comprehensive video anomaly detection and can complement each other. However, no existing model or dataset supports both tasks simultaneously. To address this, we introduce VAGU (Video Anomaly Grounding and Understanding), the first benchmark to integrate both tasks. Each VAGU instance includes annotations for anomaly category, semantic explanation, precise temporal grounding and Video QA. We also provide multiple-choice Video QA for objective evaluation. Based on this dataset, we propose Glance then Scrutinize (GtS), a training-free framework guided by textual prompts. The framework first enables coarse localization of high-probability anomalous regions, followed by detailed anomaly interpretation and temporal boundary refinement. Additionally, we propose the JeAUG metric, which jointly evaluates semantic interpretability and temporal precision, overcoming the limitations of traditional metrics. Extensive experiments verify the effectiveness of our benchmark, framework, and evaluation metric.