Training-Free From survey PDF — verify links
AnyAnomaly
AnyAnomaly — Customizable Reasoning
WACV · 2026Human-reviewed summary status
Survey summary
AnyAnomaly introduces customizable video anomaly detection (C-VAD), where user-defined text specifies the abnormal event; it performs segment-level, context-aware visual question answering with a frozen large vision-language model using key-frame selection and grid-format temporal context, without fine-tuning.
Taxonomy placement
Training-Free
Training-FreeCustomizable Reasoning
Method characteristics
Training-FreeCustomizable VADContext-aware VQAKey frames