论文标题
使用时空卷积LSTM的预测误差的异常检测
Anomaly detection using prediction error with Spatio-Temporal Convolutional LSTM
论文作者
论文摘要
在本文中，我们提出了一种新的方法，用于使用时空卷积长的短期记忆（ConvlstM）进行序列到序列预测和重建的现有体系结构的动机。就像先前关于异常检测的工作一样，异常在重建或预测中是空间定位的故障。在使用五个基准数据集的实验中，我们表明，使用预测可以使使用重建的性能出色。我们还将性能与不同的长度输入/输出序列进行比较。总体而言，我们使用预测的结果与基准数据集中的最新技术相媲美。
In this paper, we propose a novel method for video anomaly detection motivated by an existing architecture for sequence-to-sequence prediction and reconstruction using a spatio-temporal convolutional Long Short-Term Memory (convLSTM). As in previous work on anomaly detection, anomalies arise as spatially localised failures in reconstruction or prediction. In experiments with five benchmark datasets, we show that using prediction gives superior performance to using reconstruction. We also compare performance with different length input/output sequences. Overall, our results using prediction are comparable with the state of the art on the benchmark datasets.
