A skeleton-based zero-shot VAD method distills LLM knowledge for action typicality during training and performs test-time context uniqueness analysis to derive scene-adaptive normality boundaries, claiming SOTA results on four datasets with over 100 unseen scenes.
Harness- ing large language models for training-free video anomaly detection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
AAND is a two-stage anomaly detection method that advances a pre-trained teacher via residual anomaly amplification and applies hard knowledge distillation in reverse distillation to achieve SOTA results on MVTecAD, VisA, and MVTec3D-RGB.
citing papers explorer
-
Action Hints: Semantic Typicality and Context Uniqueness for Generalizable Skeleton-based Video Anomaly Detection
A skeleton-based zero-shot VAD method distills LLM knowledge for action typicality during training and performs test-time context uniqueness analysis to derive scene-adaptive normality boundaries, claiming SOTA results on four datasets with over 100 unseen scenes.
-
Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection
AAND is a two-stage anomaly detection method that advances a pre-trained teacher via residual anomaly amplification and applies hard knowledge distillation in reverse distillation to achieve SOTA results on MVTecAD, VisA, and MVTec3D-RGB.