EventVAD: Training-Free Event-Aware Video Anomaly Detection

2025-04-17

AI Summary

Video anomaly detection (VAD) faces two key challenges: supervised methods rely heavily on large-scale annotated data and suffer from poor generalization, while training-free approaches struggle to precisely localize fine-grained visual events. This paper proposes EventVAD—the first event-aware, training-free VAD framework. It models dynamic spatiotemporal relationships via a temporal decay-constrained graph and achieves fine-grained anomaly localization through signal-ratio-threshold-driven unsupervised event boundary detection. Furthermore, it introduces a hierarchical prompting strategy enhanced by event consistency to synergistically leverage multimodal large language models (7B) for semantic reasoning. Critically, EventVAD requires no training, significantly improving generalization to unseen anomalies. On UCF-Crime and XD-Violence, it achieves state-of-the-art performance under the training-free setting, outperforming not only same-scale but also larger-parameter baselines across all metrics.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Video Anomaly Detection~(VAD) focuses on identifying anomalies within videos. Supervised methods require an amount of in-domain training data and often struggle to generalize to unseen anomalies. In contrast, training-free methods leverage the intrinsic world knowledge of large language models (LLMs) to detect anomalies but face challenges in localizing fine-grained visual transitions and diverse events. Therefore, we propose EventVAD, an event-aware video anomaly detection framework that combines tailored dynamic graph architectures and multimodal LLMs through temporal-event reasoning. Specifically, EventVAD first employs dynamic spatiotemporal graph modeling with time-decay constraints to capture event-aware video features. Then, it performs adaptive noise filtering and uses signal ratio thresholding to detect event boundaries via unsupervised statistical features. The statistical boundary detection module reduces the complexity of processing long videos for MLLMs and improves their temporal reasoning through event consistency. Finally, it utilizes a hierarchical prompting strategy to guide MLLMs in performing reasoning before determining final decisions. We conducted extensive experiments on the UCF-Crime and XD-Violence datasets. The results demonstrate that EventVAD with a 7B MLLM achieves state-of-the-art (SOTA) in training-free settings, outperforming strong baselines that use 7B or larger MLLMs.

Problem

• Detecting anomalies in videos without training data
• Localizing fine-grained visual transitions and diverse events
• Improving temporal reasoning with event-aware features

Innovation

• Dynamic graph modeling with time-decay constraints
• Unsupervised statistical event boundary detection
• Hierarchical prompting strategy for MLLM reasoning