Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations.
Anil Osman TurNicola Dall'AsenCigdem BeyanElisa RicciPublished in: CoRR (2023)
Keyphrases
- anomaly detection
- diffusion models
- unsupervised anomaly detection
- unsupervised learning
- intrusion detection
- key frames
- diffusion model
- video data
- detecting anomalies
- motion estimation
- video sequences
- network intrusion detection
- image sequences
- intrusion detection system
- network anomaly detection
- moving objects
- network traffic
- information diffusion
- anomalous behavior
- video content
- motion analysis
- video frames
- negative selection algorithm
- social networks
- motion segmentation
- data mining
- influence maximization
- motion model
- optical flow
- greedy algorithm
- viral marketing
- one class support vector machines
- motion field
- supervised learning