这篇论文介绍了一种新的视频异常检测器，它具有更快的响应速度和更高的准确性，值得专业人士关注。
近期研究将Mamba风格状态空间模型（SSMs）应用于视频异常检测，但现有方法仍依赖缓冲剪辑或窗口，缺乏对时间记忆与检测延迟关系的理论解释，仅通过GPU吞吐量而非目标边缘硬件来基准效率。我们引入了一种严格因果流异常检测器，其固定大小状态每帧更新时间为O(1)，无前瞻和无剪辑缓冲。其时间核心是一个对角线性状态空间递归，具有输入和状态依赖的衰减门，通过在冻结视觉骨干上的因果下一嵌入预测进行自监督训练。我们推导出递归衰减频谱与检测延迟和可可靠捕获的最短异常之间的封闭形式关系，然后在UCSD Ped2和CUHK Avenue上进行实证验证。从学习到的基衰减（57到59帧）预测的收敛延迟界限远高于测量的检测延迟（1.6和18.4帧），表明事件边界门而不是基衰减控制响应速度。我们进一步报告了在Apple M3 Pro硬件上直接测量的端到端延迟和吞吐量，每帧0.74毫秒和0.77毫秒（超过1300 FPS），而不是模拟的GPU数字。未经调整的初始配置下，该方法在Ped2和Avenue上达到67.9%和70.2%的帧级AUC，略低于先前非因果SSM基线。在衰减率、状态大小和门控上的消融实验表明，门控贡献与数据集大小相关，在较小的Ped2训练集上损害准确性，但在较大的Avenue集上有所帮助。缩小准确性差距并将评估扩展到第三个更大的基准是下一步的紧急任务。
Strictly Causal Streaming Video Anomaly Detection with a Theoretically-Grounded State-Space Core
Recent work has applied Mamba style state space models (SSMs) to video anomaly detection, yet existing approaches still rely on buffering clips or windows internally, lack a theoretical account of how temporal memory relates to detection latency, and benchmark efficiency only through GPU throughput rather than the edge hardware these methods are intended to target. We introduce a strictly causal streaming anomaly detector whose fixed size state is updated in O(1) time and memory per incoming frame, with no lookahead and no clip buffering. Its temporal core is a diagonal linear state space recurrence with an input and state dependent decay gate, trained self supervised through causal next embedding prediction on a frozen visual backbone. We derive a closed form relationship between the recurrence decay spectrum and both detection delay and the shortest anomaly it can reliably capture, then validate empirically on UCSD Ped2 and CUHK Avenue. The settling delay bound predicted from the learned base decay (57 to 59 frames) sits far above the measured detection delay (1.6 and 18.4 frames), showing that the event boundary gate, not the base decay, governs responsiveness. We further report end to end latency and throughput measured directly on Apple M3 Pro hardware, 0.74 ms and 0.77 ms per frame (over 1300 FPS), rather than simulated GPU numbers. With an untuned initial configuration the method reaches 67.9 percent and 70.2 percent frame level AUC on Ped2 and Avenue, trailing prior non causal SSM baselines in accuracy. Ablations over decay rate, state size, and gating reveal that the gate contribution is dataset size dependent, hurting accuracy on the smaller Ped2 training set but helping on the larger Avenue one. Closing this accuracy gap and extending evaluation to a third, larger benchmark are immediate next steps.