Reliability-Aware Prototype Calibration for Frozen Pose-Flow Video Anomaly Detection
For practitioners using cached pose-flow anomaly detection systems where retraining is impractical, RPC provides a lightweight post-hoc calibration method to improve ranking accuracy.
The paper tackles the problem of improving likelihood-based rankings in frozen pose-flow video anomaly detectors, which suffer from multimodal normal behavior and pose noise. Reliability-Aware Prototype Calibration (RPC) achieves frame-level AUROC gains of 0.34 to 4.49 percentage points (average 2.03) across eight backbone-dataset pairs.
Pose-flow video anomaly detectors are attractive for one-class surveillance because they provide likelihood-based rankings for tracked skeleton windows. However, a single likelihood score may hide multimodal normal behavior and be sensitive to pose-observation noise. We study a frozen-detector setting in which the pose-flow backbone, cached skeleton tracks, and evaluation pipeline are fixed. Reliability-Aware Prototype Calibration (RPC) is a post-hoc score calibration method for this setting. It adds a standardized nearest-prototype deviation in the frozen latent space to the standardized flow score, and uses keypoint confidence only to gate this added geometric evidence. Thus, RPC preserves the original density signal while correcting the ranking with empirical normal-mode structure under pose reliability. Across two frozen pose-flow backbones and four datasets, RPC improves frame-level AUROC in all eight backbone-dataset pairs, with gains ranging from 0.34 to 4.49 percentage points and averaging 2.03 points. Ablation and reliability analyses show that prototype deviation is the main corrective signal, while reliability gating is most useful when pose observations are less trustworthy. These results suggest that lightweight post-hoc calibration can strengthen cached pose-flow systems when retraining or reproducing the full pose pipeline is impractical.