Lightweight Multiscale Spatiotemporal Locally Connected Graph Convolutional Networks for Single Human Motion Forecasting.
Di-Hua ZhaiZigeng YanYuanqing XiaPublished in: IEEE Trans Autom. Sci. Eng. (2024)
Keyphrases
- lightweight
- human motion
- multiscale
- human body
- motion capture
- video sequences
- gait recognition
- optical motion capture
- spatio temporal
- human motion tracking
- human movement
- motion sequences
- body parts
- image sequences
- motion capture data
- motion recognition
- social networks
- wireless sensor networks
- image segmentation
- communication infrastructure
- three dimensional
- motion history images
- graph structure
- space time
- multivariate time series
- image representation
- probabilistic model
- development environments
- human motion analysis
- human movements
- motion synthesis
- machine learning