TAM-Net: Temporal Enhanced Appearance-to-Motion Generative Network for Video Anomaly Detection.
Xiangli JiBairong LiYuesheng ZhuPublished in: IJCNN (2020)
Keyphrases
- anomaly detection
- network traffic
- dynamic textures
- spatial and temporal
- network anomaly detection
- space time
- object motion
- intrusion detection
- detect anomalies
- network intrusion
- temporal continuity
- detecting anomalies
- network intrusion detection
- intrusion prevention
- unsupervised learning
- intrusion detection system
- anomalous behavior
- computer networks
- network security
- video frames
- optical flow
- motion model
- one class support vector machines
- generative model
- moving objects
- detecting anomalous
- layered representation
- normal behavior
- key frames
- behavior analysis
- motion estimation
- video sequences
- negative selection algorithm
- image sequences
- video surveillance
- video data
- feature selection
- network structure
- training data