Adaptive most joint selection and covariance descriptions for a robust skeleton-based human action recognition.
Van-Toi NguyenTien-Nam NguyenThi-Lan LeDinh-Tan PhamHai VuPublished in: Multim. Tools Appl. (2021)
Keyphrases
- action recognition
- static images
- view invariant
- human actions
- human movements
- bag of words
- human activities
- human detection
- spatio temporal interest points
- computer vision
- action classification
- spatial temporal
- body parts
- human object interactions
- recognizing human actions
- activity recognition
- motion capture data
- motion history images
- bag of features
- recognition of human actions
- view invariant action recognition
- high level
- depth sensors
- human pose
- action primitives
- recognizing actions
- robust tracking
- independent subspace analysis
- video sequences