AI RESEARCH
Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets
arXiv CS.CV
•
ArXi:2603.24991v1 Announce Type: new Event-based vision, characterized by low redundancy, focus on dynamic motion, and inherent privacy-preserving properties, naturally fits the demands of video anomaly detection (VAD). However, the absence of dedicated event-stream anomaly detection datasets and effective modeling strategies has significantly hindered progress in this field. In this work, we take the first major step toward establishing event-based VAD as a unified research direction.