Guo-Long Li

Spatiotemporal reverse distillation with memory-augmented pseudo-anomaly learning for unsupervised video anomaly detection

SupCL-GNN: Supervised contrastive learning with graph neural networks for enhanced encrypted traffic classification

Enhancing video anomaly detection through dual-path reconstruction and diverse pseudo-anomaly generation

This paper introduces a VAD method leveraging a multi-source pseudo-anomaly generator and a dual-decoder framework that integrates spatiotemporal perturbations and object-level local appearance perturbations to enhance anomaly coverage.