PPT: Token-Pruned Pose Transformer for Monocular and Multi-view Human Pose Estimation.
Haoyu MaZhe WangYifei ChenDeying KongLiangjian ChenXingwei LiuXiangyi YanHao TangXiaohui XiePublished in: ECCV (5) (2022)
Keyphrases
- multi view
- human pose estimation
- pose estimation
- d objects
- human pose
- single view
- multiple views
- body parts
- pose parameters
- depth map
- human body
- depth images
- computer vision
- body pose
- three dimensional
- object recognition
- semi supervised
- viewpoint
- gaussian processes
- motion capture
- range images
- visual hull
- markerless
- action recognition
- feature space
- human detection
- learning tasks
- learning algorithm