AI RESEARCH
Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models
arXiv CS.CV
•
ArXi:2605.12725v1 Announce Type: new Recent video anomaly detection research has expanded rapidly with an emphasis on general models of normality intended to work across many different scenes. While this focus has led to improvements in scalability and multi-scene generalization, it has also shifted the field away from modeling the scene-specific and context-dependent nature of normal behavior.