A Unified Deep Framework for Joint 3D Pose Estimation and Action Recognition from a Single RGB Camera.
Huy-Hieu PhamHoussam SalmaneLouahdi KhoudourAlain CrouzilSergio A. VelastinPablo ZegersPublished in: Sensors (2020)
Keyphrases
- action recognition
- human pose
- activity recognition
- human actions
- video dataset
- depth cameras
- bag of words
- probabilistic model
- computer vision
- action recognition in videos
- recognition of human actions
- view invariant action recognition
- recognizing human actions
- depth sensors
- action classification
- human detection
- low level
- spatio temporal