An autoregressive denoising score matching method, combining scene, motion, and appearance cues, achieves state-of-the-art video anomaly detection on Avenue, ShanghaiTech, and NWPU Campus.
A new comprehensive benchmark for semi-supervised video anomaly detection and anticipation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Autoregressive Denoising Score Matching is a Good Video Anomaly Detector
An autoregressive denoising score matching method, combining scene, motion, and appearance cues, achieves state-of-the-art video anomaly detection on Avenue, ShanghaiTech, and NWPU Campus.