VigilFormer: 用于视频异常检测的可变形注意力与因果风险推理
VigilFormer: Deformable Attention for Video Anomaly Detection with Causal Risk Inference
AI总结：
提出VigilFormer框架，结合可变形时空注意力与因果时序建模，通过稀疏注意力、对比多实例学习和自适应帧跳过，在保持高精度的同时实现实时异常检测。
摘要：
监控场景中的视频异常检测必须在检测准确性与实时吞吐量之间取得平衡，现有方法要么通过更强的特征提取器，要么通过更高效的架构来解决这一矛盾，但很少能兼顾两者。我们提出VigilFormer，一个统一框架，结合可变形时空注意力与因果时序建模，用于检测未修剪监控视频中的异常。所提出的可变形时空编码器（DSTE）关注跨帧的稀疏信息位置，避免了密集注意力的二次复杂度，同时保留了捕捉不规则运动模式的能力。因果异常分类器（CAC）对片段级特征应用扩张因果卷积，并优化对比多实例学习目标，无需帧级标签即可分离异常和正常表示。为满足部署约束，自适应置信度调度器（ACS）在推理时动态跳过低信息帧，减少静态场景中的冗余计算。在UCF-Crime、ShanghaiTech和CUHK Avenue上评估，VigilFormer在单GPU上以41.5 FPS分别达到87.83%、97.21%和89.74%的AUC分数，在准确性和速度上均优于最近的弱监督方法。
英文摘要：
Video anomaly detection in surveillance settings must balance detection accuracy against real-time throughput, a tension that existing methods address either through stronger feature extractors or more efficient architectures, but rarely both. We present VigilFormer, a unified framework that combines deformable spatio-temporal attention with causal temporal modeling to detect anomalies in untrimmed surveillance video. The proposed Deformable Spatio-Temporal Encoder (DSTE) attends to a sparse set of informative locations across frames, avoiding the quadratic cost of dense attention while retaining the ability to capture irregular motion patterns. A Causal Anomaly Classifier (CAC) applies dilated causal convolutions over snippet-level features and optimizes a contrastive multiple-instance learning objective that separates anomalous and normal representations without frame-level labels. To meet deployment constraints, an Adaptive Confidence Scheduler (ACS) dynamically skips low-information frames at inference time, reducing redundant computation in static scenes. Evaluated on UCF-Crime, ShanghaiTech, and CUHK Avenue, VigilFormer achieves AUC scores of 87.83%, 97.21%, and 89.74% respectively, at 41.5 FPS on a single GPU, outperforming recent weakly-supervised methods in both accuracy and speed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
