# Reliability-Aware Prototype Calibration for Frozen Pose-Flow Video Anomaly Detection

arXiv: https://arxiv.org/abs/2606.20312 · HTML: https://mlsanity.com/paper/2606.20312/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Why Normalizing Flows Fail to Detect Out-of-Distribution Data](https://mlsanity.com/paper/2006.08545/) (2020)
- [Whole-Body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2007.11858/) (2020)
- [PoseTrack: A Benchmark for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1710.10000/) (2017)
- [Anomaly Detection in Video via Self-Supervised and Multi-Task Learning](https://mlsanity.com/paper/2011.07491/) (2020)
- [Graph Embedded Pose Clustering for Anomaly Detection](https://mlsanity.com/paper/1912.11850/) (2019)
- [UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection](https://mlsanity.com/paper/2111.08644/) (2021)
- [Normalizing Flows for Human Pose Anomaly Detection](https://mlsanity.com/paper/2211.10946/) (2022)
- [Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models](https://mlsanity.com/paper/2302.05087/) (2023)
- [Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models](https://mlsanity.com/paper/2407.10299/) (2024)
- [Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors](https://mlsanity.com/paper/2306.12041/) (2023)
- [Networking Systems for Video Anomaly Detection: A Tutorial and Survey](https://mlsanity.com/paper/2405.10347/) (2024)
- [Visual Anomaly Detection Via Partition Memory Bank Module and Error Estimation](https://mlsanity.com/paper/2209.12441/) (2022)
- [An Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Prediction](https://mlsanity.com/paper/2406.15395/) (2024)
- [Holistic Representation Learning for Multitask Trajectory Anomaly Detection](https://mlsanity.com/paper/2311.01851/) (2023)
- [AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM](https://mlsanity.com/paper/2503.04504/) (2025)
- [Contracting Skeletal Kinematics for Human-Related Video Anomaly Detection](https://mlsanity.com/paper/2301.09489/) (2023)
- [Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model](https://mlsanity.com/paper/2412.09026/) (2024)
- [Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data](https://mlsanity.com/paper/2310.10461/) (2023)
- [VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection](https://mlsanity.com/paper/2409.16225/) (2024)
- [DA-Flow: Dual Attention Normalizing Flow for Skeleton-based Video Anomaly Detection](https://mlsanity.com/paper/2406.02976/) (2024)
- [Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detection](https://mlsanity.com/paper/2506.18368/) (2025)
- [Action Hints: Semantic Typicality and Context Uniqueness for Generalizable Skeleton-based Video Anomaly Detection](https://mlsanity.com/paper/2509.11058/) (2025)

## Abstract (arXiv)

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.