STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences.
Soroush MehrabanMohammad Javad RajabiBabak TaatiPublished in: CoRR (2024)
Keyphrases
- action recognition
- activity recognition
- bag of words
- human actions
- computer vision
- human detection
- motion capture data
- motion history images
- body parts
- static images
- spatial temporal
- view invariant
- video dataset
- bag of features
- recognition of human actions
- human pose
- action classification
- recognizing human actions
- depth sensors
- motion features
- hidden markov models
- viewpoint
- action primitives
- action recognition in videos
- independent subspace analysis
- machine learning
- recognizing actions
- depth cameras
- human activities
- high level
- mid level
- view invariant action recognition