TASG-VAD: Weakly Supervised Video Anomaly Detection via Temporal Variation Attention and Adaptive Saliency Guidance

Abstract

Weakly supervised video anomaly detection (WSVAD) is important in intelligent surveillance. Existing methods often overemphasize salient abnormal segments, overlook subtle clues, and model temporal dependencies ineffectively. To address these issues, we propose TASG-VAD, an efficient anomaly detection framework. The proposed method is developed along two main directions: dual-scale temporal modeling and subtle anomaly discovery. Specifically, Temporal Variation Attention (TVA) amplifies anomaly related dynamic changes through second-order temporal differences while suppressing interference from static backgrounds. In addition, the Dual-Scale Temporal Encoder (DSTE) combines a dual-branch structure, a parameter-free attention mechanism, and dual-scale temporal convolutions to simultaneously capture local fine-grained fluctuations and long range global dependencies. Furthermore, to alleviate the model’s reliance on dominant anomalous segments, TASG-VAD introduces an Adaptive Saliency Guidance (ASG) strategy, which performs intra-video saliency ranking and dynamic masking to guide the model toward overlooked subtle anomalies. Experimental results show that TASG-VAD achieves AUCs of 88.21% and 98.38% on UCF-Crime and ShanghaiTech, respectively, and an AP of 84.60% on XD-Violence. With only about 1.7M parameters, it maintains high accuracy and excellent inference efficiency, and significantly outperforms existing methods.