Adding Multi-modal Controls to Whole-body Human Motion Generation.
Yuxuan BianAiling ZengXuan JuXian LiuZhaoyang ZhangWei LiuQiang XuPublished in: CoRR (2024)
Keyphrases
- multi modal
- human motion
- humanoid robot
- motion capture
- human body
- video sequences
- body parts
- optical motion capture
- motion recognition
- image sequences
- spatio temporal
- multi modality
- motion sequences
- motion capture data
- human actions
- high dimensional
- viewpoint
- cross modal
- motion synthesis
- semantic concepts
- low level
- three dimensional
- uni modal
- machine learning