RPC is a post-hoc calibration technique that augments flow-based anomaly scores with nearest-prototype deviation in the frozen latent space, gated by keypoint confidence, yielding consistent AUROC gains on video anomaly detection tasks.
Model selection of anomaly detectors in the absence of labeled validation data.arXiv preprint arXiv:2310.10461, 2023
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
AUCp selects inference models for unsupervised abnormality detection by computing AUC after labeling all test samples as positive, shown to outperform conventional metrics when normal training data is representative.
citing papers explorer
-
Reliability-Aware Prototype Calibration for Frozen Pose-Flow Video Anomaly Detection
RPC is a post-hoc calibration technique that augments flow-based anomaly scores with nearest-prototype deviation in the frozen latent space, gated by keypoint confidence, yielding consistent AUROC gains on video anomaly detection tasks.
-
AUCp: Pseudo-AUC for Inference Model Selection with Unlabeled Validation Data in Abnormality Detection
AUCp selects inference models for unsupervised abnormality detection by computing AUC after labeling all test samples as positive, shown to outperform conventional metrics when normal training data is representative.