GIAD-ST: Detecting anomalies in human monitoring based on generative inpainting via self-supervised multi-task learning.
Ning DongEinoshin SuzukiPublished in: J. Intell. Inf. Syst. (2022)
Keyphrases
- multi task learning
- detecting anomalies
- multi task
- abnormal events
- anomaly detection
- multiple tasks
- learning tasks
- learning problems
- gaussian processes
- transfer learning
- theoretical analysis
- high order
- inductive learning
- multitask learning
- generative model
- reinforcement learning
- decision trees
- data sets
- em algorithm
- metric learning
- similarity measure
- real world