Motion Semantics Guided Normalizing Flow for Privacy-Preserving Video Anomaly Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915895497981952 |
|---|---|
| author | Liu, Yang Chen, Boan Meng, Yuanyuan Liu, Jing Guo, Zhengliang Zhou, Wei Sun, Peng Chen, Hong |
| author_facet | Liu, Yang Chen, Boan Meng, Yuanyuan Liu, Jing Guo, Zhengliang Zhou, Wei Sun, Peng Chen, Hong |
| contents | As embodied perception systems increasingly bridge digital and physical realms in interactive multimedia applications, the need for privacy-preserving approaches to understand human activities in physical environments has become paramount. Video anomaly detection is a critical task in such embodied multimedia systems for intelligent surveillance and forensic analysis. Skeleton-based approaches have emerged as a privacy-preserving alternative that processes physical world information through abstract human pose representations while discarding sensitive visual attributes such as identity and facial features. However, existing skeleton-based methods predominantly model continuous motion trajectories in a monolithic manner, failing to capture the hierarchical nature of human activities composed of discrete semantic primitives and fine-grained kinematic details, which leads to reduced discriminability when anomalies manifest at different abstraction levels. In this regard, we propose Motion Semantics Guided Normalizing Flow (MSG-Flow) that decomposes skeleton-based VAD into hierarchical motion semantics modeling. It employs vector quantized variational auto-encoder to discretize continuous motion into interpretable primitives, an autoregressive Transformer to model semantic-level temporal dependencies, and a conditional normalizing flow to capture detail-level pose variations. Extensive experiments on benchmarks (HR-ShanghaiTech & HR-UBnormal) demonstrate that MSG-Flow achieves state-of-the-art performance with 88.1% and 75.8% AUC respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_26745 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Motion Semantics Guided Normalizing Flow for Privacy-Preserving Video Anomaly Detection Liu, Yang Chen, Boan Meng, Yuanyuan Liu, Jing Guo, Zhengliang Zhou, Wei Sun, Peng Chen, Hong Computer Vision and Pattern Recognition As embodied perception systems increasingly bridge digital and physical realms in interactive multimedia applications, the need for privacy-preserving approaches to understand human activities in physical environments has become paramount. Video anomaly detection is a critical task in such embodied multimedia systems for intelligent surveillance and forensic analysis. Skeleton-based approaches have emerged as a privacy-preserving alternative that processes physical world information through abstract human pose representations while discarding sensitive visual attributes such as identity and facial features. However, existing skeleton-based methods predominantly model continuous motion trajectories in a monolithic manner, failing to capture the hierarchical nature of human activities composed of discrete semantic primitives and fine-grained kinematic details, which leads to reduced discriminability when anomalies manifest at different abstraction levels. In this regard, we propose Motion Semantics Guided Normalizing Flow (MSG-Flow) that decomposes skeleton-based VAD into hierarchical motion semantics modeling. It employs vector quantized variational auto-encoder to discretize continuous motion into interpretable primitives, an autoregressive Transformer to model semantic-level temporal dependencies, and a conditional normalizing flow to capture detail-level pose variations. Extensive experiments on benchmarks (HR-ShanghaiTech & HR-UBnormal) demonstrate that MSG-Flow achieves state-of-the-art performance with 88.1% and 75.8% AUC respectively. |
| title | Motion Semantics Guided Normalizing Flow for Privacy-Preserving Video Anomaly Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.26745 |