Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community, with promising applications in areas such as information forensics and public safety protection. Due to the rarity and diversity of anomalies, existing methods only use easily collected regular events to model the inherent normality of normal spatial-temporal patterns in an unsupervised manner. Previous studies have shown that existing unsupervised VAD models are incapable of label-independent data offsets (e.g., scene changes) in real-world scenarios and may fail to respond to light anomalies due to the overgeneralization of deep neural networks. Inspired by causality learning, we argue that there exist causal factors that can adequately generalize the prototypical patterns of regular events and present significant deviations when anomalous instances occur. In this regard, we propose Causal Representation Consistency Learning (CRCL) to implicitly mine potential scene-robust causal variable in unsupervised video normality learning. Specifically, building on the structural causal models, we propose scene-debiasing learning and causality-inspired normality learning to strip away entangled scene bias in deep representations and learn causal video normality, respectively. Extensive experiments on benchmarks validate the superiority of our method over conventional deep representation learning. Moreover, ablation studies and extension validation show that the CRCL can cope with label-independent biases in multi-scene settings and maintain stable performance with only limited training data available.

翻译：视频异常检测（VAD）是视频理解领域一项基础而艰巨的任务，在信息取证和公共安全保护等领域具有广阔的应用前景。由于异常的罕见性和多样性，现有方法仅利用易于收集的常规事件，以无监督方式对正常时空模式的内在规律性进行建模。先前研究表明，现有的无监督VAD模型无法处理现实场景中与标签无关的数据偏移（例如场景变化），并且由于深度神经网络的过度泛化，可能对轻微异常失效。受因果学习的启发，我们认为存在能够充分泛化常规事件原型模式并在异常实例发生时呈现显著偏差的因果因子。为此，我们提出因果表示一致性学习（CRCL），以在无监督视频规律性学习中隐式挖掘潜在的场景鲁棒因果变量。具体而言，基于结构因果模型，我们分别提出场景去偏学习和因果启发的规律性学习，以剥离深度表示中纠缠的场景偏差并学习因果视频规律性。在基准数据集上的大量实验验证了本方法相较于传统深度表示学习的优越性。此外，消融研究和扩展验证表明，CRCL能够处理多场景设置中与标签无关的偏差，并在仅有限训练数据可用时保持稳定的性能。