A patch-level diffusion predictor with appearance and temporal-difference motion conditions achieves 98.6, 91.3, 79.2, and 63.4 frame-level AUC on Ped2, Avenue, ShanghaiTech, and UBnormal.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model
A patch-level diffusion predictor with appearance and temporal-difference motion conditions achieves 98.6, 91.3, 79.2, and 63.4 frame-level AUC on Ped2, Avenue, ShanghaiTech, and UBnormal.