Using Direct Acyclic Graphs to Enhance Skeleton-Based Action Recognition with a Linear-Map Convolution Neural Network.
Tan-Hsu TanJin-Hao HusShing-Hong LiuYung-Fa HuangMunkhjargal GochooPublished in: Sensors (2021)
Keyphrases
- action recognition
- neural network
- human actions
- bag of words
- human detection
- activity recognition
- action classification
- computer vision
- static images
- body parts
- bag of features
- image processing
- spatial temporal
- view invariant
- human activities
- video dataset
- recognizing human actions
- independent subspace analysis
- view invariant action recognition
- depth sensors
- recognizing actions
- human pose
- video data
- visual features
- multi class
- image features
- low level
- video sequences
- machine learning