Abstract
Weakly supervised video anomaly detection (WS-VAD) involves identifying the temporal intervals that contain anomalous events in untrimmed videos, where only video-level annotations are provided as supervisory signals. However, a key limitation persists in WS-VAD, as dense frame-level annotations are absent, which often leaves existing methods struggling to learn anomaly semantics effectively. To address this issue, we propose a novel framework named LAS-VAD, short for Learning Anomaly Semantics for WS-VAD, which integrates anomaly-connected component mechanism and intention awareness mechanism. The former is designed to assign video frames into distinct semantic groups within a video, and frame segments within the same group are deemed to share identical semantic information. The latter leverages an intention-aware strategy to distinguish between similar normal and abnormal behaviors (e.g., taking items and stealing). To further model the semantic information of anomalies, as anomaly occurrence is accompanied by distinct characteristic attributes (i.e., explosions are characterized by flames and thick smoke), we additionally incorporate anomaly attribute information to guide accurate detection. Extensive experiments on two benchmark datasets, XD-Violence and UCF-Crime, demonstrate that our LAS-VAD outperforms current state-of-the-art methods with remarkable gains.
Abstract (translated)
弱监督视频异常检测（WS-VAD）旨在识别未修剪视频中包含异常事件的时间间隔，仅使用视频级别的标注作为监督信号。然而，在这种情况下，由于缺少密集的帧级注释，现有的方法在有效学习异常语义方面面临挑战。为了解决这个问题，我们提出了一种新的框架——用于弱监督视频异常检测（WS-VAD）的学习异常语义框架（LAS-VAD），该框架结合了异常连接组件机制和意图感知机制。 异常连接组件机制旨在将视频帧分配到视频内的不同语义组中，并认为同一组中的帧片段共享相同的语义信息。而意图感知策略则通过识别类似但不同的正常行为与异常行为（例如，取物品和偷窃）之间的区别来提高检测准确性。 此外，为了进一步建模异常的语义信息——因为异常发生时伴随着独特的特征属性（如爆炸事件具有火焰和浓烟等特定属性），我们还整合了异常属性信息以指导准确检测。在两个基准数据集XD-Violence和UCF-Crime上进行的大量实验表明，我们的LAS-VAD方法比当前最先进的方法有显著的性能提升。
URL
https://arxiv.org/abs/2603.00550
