A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completion.
Junkun JiangJie ChenYike GuoPublished in: CoRR (2022)
Keyphrases
- spatial temporal
- motion capture
- human motion
- human actions
- human body
- spatio temporal
- human figure
- multi view
- spatial and temporal
- computer graphics
- human motion capture
- action recognition
- human computer interaction
- temporal information
- motion capture data
- image sequences
- video shots
- video sequences
- spatial information
- three dimensional
- space time
- humanoid robot