脉冲神经网络

面向高效视频异常检测的跨架构跨模态知识蒸馏方法研究
构建跨架构、跨模态的双向知识蒸馏框架，在 RGB/DVS 数据上提升 CNN 表征与 SNN 在视频监控异常检测中的性能。
面向高效视频异常检测的跨架构跨模态知识蒸馏方法研究
UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networks
We introduce UCF-Crime-DVS, the first DVS video anomaly detection benchmark, and a multi-scale spiking fusion network for weakly supervised video anomaly detection.
PDF 引用 代码 数据集 源文档 项目 DOI AAAI
UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networks