Approximate structured output learning for Constrained Local Models with application to real-time facial feature detection and tracking on low-power devices.
Shuai ZhengPaul SturgessPhilip H. S. TorrPublished in: FG (2013)
Keyphrases
- structured output
- low power
- real time
- structured prediction
- low cost
- low power consumption
- power consumption
- high speed
- facial feature detection
- supervised learning
- prior knowledge
- maximum margin
- latent variable models
- learning tasks
- learning models
- learning algorithm
- multi task learning
- object detection
- conditional random fields
- probabilistic model
- highly efficient
- bayesian networks
- multiclass classification
- computer vision
- machine learning