# From Frames to Events: Rethinking Evaluation in Human-Centric Video Anomaly Detection

arXiv: https://arxiv.org/abs/2604.09327 · HTML: https://mlsanity.com/paper/2604.09327/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [Graph Embedded Pose Clustering for Anomaly Detection](https://mlsanity.com/paper/1912.11850/) (2019)
- [Normalizing Flows for Human Pose Anomaly Detection](https://mlsanity.com/paper/2211.10946/) (2022)
- [Multi-timescale Trajectory Prediction for Abnormal Human Activity Detection](https://mlsanity.com/paper/1908.04321/) (2019)
- [A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation](https://mlsanity.com/paper/2305.13611/) (2023)
- [A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos](https://mlsanity.com/paper/2112.04294/) (2021)
- [Online Anomaly Detection in Surveillance Videos with Asymptotic Bounds on False Alarm Rate](https://mlsanity.com/paper/2010.07110/) (2020)
- [Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection](https://mlsanity.com/paper/2112.03649/) (2021)
- [An Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Prediction](https://mlsanity.com/paper/2406.15395/) (2024)
- [CHAD: Charlotte Anomaly Dataset](https://mlsanity.com/paper/2212.09258/) (2022)
- [Skeletal Video Anomaly Detection using Deep Learning: Survey, Challenges and Future Directions](https://mlsanity.com/paper/2301.00114/) (2022)
- [Evaluating the Effectiveness of Video Anomaly Detection in the Wild: Online Learning and Inference for Real-world Deployment](https://mlsanity.com/paper/2404.18747/) (2024)
- [Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmark](https://mlsanity.com/paper/2408.14329/) (2024)
- [Human-Centric Video Anomaly Detection Through Spatio-Temporal Pose Tokenization and Transformer](https://mlsanity.com/paper/2408.15185/) (2024)
- [Shopformer: Transformer-Based Framework for Detecting Shoplifting via Human Pose](https://mlsanity.com/paper/2504.19970/) (2025)
- [Skeleton Motion Words for Unsupervised Skeleton-Based Temporal Action Segmentation](https://mlsanity.com/paper/2508.04513/) (2025)
- [From Lab to Field: Real-World Evaluation of an AI-Driven Smart Video Solution to Enhance Community Safety](https://mlsanity.com/paper/2312.02078/) (2023)
- [Exploring Public's Perception of Safety and Video Surveillance Technology: A Survey Approach](https://mlsanity.com/paper/2312.06707/) (2023)
- [ALFred: An Active Learning Framework for Real-world Semi-supervised Anomaly Detection with Adaptive Thresholds](https://mlsanity.com/paper/2508.09058/) (2025)
- [From Offline to Periodic Adaptation for Pose-Based Shoplifting Detection in Real-world Retail Security](https://mlsanity.com/paper/2603.04723/) (2026)
- [Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild](https://mlsanity.com/paper/2603.04727/) (2026)

## Built on by (most cited first, 1 of 1)

- [Auditing Frame-Level AUC in Weakly Supervised Video Anomaly Detection: Granularity, Resolution, and Scene Bias](https://mlsanity.com/paper/2608.11985/) (2026)

## Abstract (arXiv)

Pose-based Video Anomaly Detection (VAD) has gained significant attention for its privacy-preserving nature and robustness to environmental variations. However, traditional frame-level evaluations treat video as a collection of isolated frames, fundamentally misaligned with how anomalies manifest and are acted upon in the real world. In operational surveillance systems, what matters is not the flagging of individual frames, but the reliable detection, localization, and reporting of a coherent anomalous event, a contiguous temporal episode with an identifiable onset and duration. Frame-level metrics are blind to this distinction, and as a result, they systematically overestimate model performance for any deployment that requires actionable, event-level alerts. In this work, we propose a shift toward an event-centric perspective in VAD. We first audit widely used VAD benchmarks, including SHT[19], CHAD[6], NWPUC[4], and HuVAD[25], to characterize their event structure. We then introduce two strategies for temporal event localization: a score-refinement pipeline with hierarchical Gaussian smoothing and adaptive binarization, and an end-to-end Dual-Branch Model that directly generates event-level detections. Finally, we establish the first event-based evaluation standard for VAD by adapting Temporal Action Localization metrics, including tIoU-based event matching and multi-threshold F1 evaluation. Our results quantify a substantial performance gap: while all SoTA models achieve frame-level AUC-ROC exceeding 52% on the NWPUC[4], their event-level localization precision falls below 10% even at a minimal tIoU=0.2, with an average event-level F1 of only 0.11 across all thresholds. The code base for this work is available at https://github.com/TeCSAR-UNCC/EventCentric-VAD.