SUVAD: Semantic Understanding Based Video Anomaly Detection Using MLLM

Video anomaly detection (VAD) aims at detecting anomalous events in videos. Most existing VAD methods distinguish anomalies by learning visual features of the video, which usually face several challenges in real-world applications. First, these methods are mostly scene-dependent, whose performances degrade obviously once the scene changes. Second, these methods are incapable of giving explanations to the detected anomalies. Third, these methods cannot adjust definitions of normal or abnormal events during test time without retraining the model. One important reason for the drawbacks is that these visual-based methods mainly detect anomalies by fitting visual patterns rather than semantically understanding the events in videos. In this paper, we propose a training-free method named Semantic Understanding based Video Anomaly Detection (SUVAD) using multi-modal large language model (MLLM). By exploiting MLLMs to generate detailed texture descriptions for videos, SUVAD achieves semantic video understanding, and then detects anomalies directly by large language models. We also designed several techniques to mitigate the hallucination problem of MLLMs. Compared to the methods based on visual features, SUVAD obtains obviously better scene generalization, anomaly interpretability, and the ability of flexible adjustment of anomaly definitions. We evaluate our method on five mainstream datasets. The results show that SUVAD achieves the best performance among all the training-free methods.