Improved Text-Driven Human Motion Generation via Out-of-Distribution Detection and Rectification.
Yiyu FuBaoquan ZhaoChenlei LvGuanghui YueRuomei WangFan ZhouPublished in: CVM (1) (2024)
Keyphrases
- human motion
- human body
- motion capture
- image sequences
- video sequences
- spatio temporal
- optical motion capture
- motion recognition
- human actions
- human motion analysis
- dynamical model
- human motion tracking
- articulated motion
- human movement
- motion capture data
- articulated body
- human movements
- gait recognition
- motion sequences
- body parts
- temporal segmentation
- event detection
- human detection
- computer vision
- visual data
- object detection
- viewpoint
- motion synthesis
- three dimensional