Do As I Do: Transferring Human Motion and Appearance between Monocular Videos with Spatial and Temporal Constraints.
Thiago L. GomesRenato MartinsJoão P. K. FerreiraErickson R. NascimentoPublished in: WACV (2020)
Keyphrases
- human motion
- view invariant
- video sequences
- image sequences
- articulated human motion
- human actions
- motion capture data
- motion capture
- human motion analysis
- human pose
- static images
- human body
- optical motion capture
- spatio temporal
- human body parts
- motion sequences
- dynamic textures
- body pose
- body parts
- human motion tracking
- visual data
- moving camera
- pose estimation
- motion history images
- video frames
- temporal segmentation
- pose tracking
- gait recognition
- appearance model
- video content
- ego motion
- motion recognition
- video data
- human movements
- markerless
- camera motion
- motion trajectories
- transfer learning
- optical flow
- motion model
- articulated body
- computer vision
- motion estimation
- motion cues
- facial expressions
- appearance information
- human pose estimation
- motion synthesis
- machine learning
- moving objects
- motion analysis