An End-to-End Multi-Task and Fusion CNN for Inertial-Based Gait Recognition.
Ruben Delgado-EscanoFrancisco M. CastroJulián Ramos CózarManuel J. Marín-JiménezNicolás GuilPublished in: IEEE Access (2019)
Keyphrases
- end to end
- multi task
- gait recognition
- multi task learning
- learning tasks
- human motion
- multi class
- principal component analysis
- background subtraction
- transfer learning
- feature selection
- learning problems
- metric learning
- object detection
- machine learning
- neural network
- computer vision
- multiple features
- multi sensor
- kernel methods
- learning algorithm
- maximum likelihood