Acquisition of Optimal Connection Patterns for Skeleton-based Action Recognition with Graph Convolutional Networks.
Katsutoshi ShirakiTsubasa HirakawaTakayoshi YamashitaHironobu FujiyoshiPublished in: VISIGRAPP (5: VISAPP) (2020)
Keyphrases
- action recognition
- human actions
- human detection
- action classification
- bag of words
- spatial temporal
- computer vision
- recognizing human actions
- body parts
- activity recognition
- recognition of human actions
- recognizing actions
- depth sensors
- view invariant
- static images
- graph structure
- human activities
- video dataset
- independent subspace analysis
- space time interest points
- view invariant action recognition
- human pose
- action detection
- sparse coding
- space time