CoReVAD applies a single frozen VLM with local response cleaning and temporal refinement steps to deliver competitive training-free video anomaly detection plus explanations on UCF-Crime and XD-Violence.
In: Proceedings of the AAAI conference on artificial intelligence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection
CoReVAD applies a single frozen VLM with local response cleaning and temporal refinement steps to deliver competitive training-free video anomaly detection plus explanations on UCF-Crime and XD-Violence.