.png){kind=icon}
.png){kind=icon}
Return
Frequency-guided multi-level human action anomaly detection with normalizing flows
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2025.112770.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We introduce a new task, human action anomaly detection, which regards the anomaly as specific action categories for human motion. • We propose to address this task under a novel frequency-guided detection framework formulated by normalizing flow. • We incorporate a multi-level detection pipeline into our model to facilitate a better learning of local anomalous action patterns.
Keywords:
Human action anomaly detection
One-class classification
Multi-level action learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
View more organizations