View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose.
Ting LiuJennifer J. SunLong ZhaoJiaping ZhaoLiangzhe YuanYuxiao WangLiang-Chieh ChenFlorian SchroffHartwig AdamPublished in: Int. J. Comput. Vis. (2022)
Keyphrases
- human pose
- view invariant
- action recognition
- human actions
- human motion
- body parts
- human detection
- human body
- activity recognition
- pose estimation
- video sequences
- computer vision
- motion capture data
- spatio temporal
- space time
- bayesian networks
- human activities
- single view
- visual features
- latent variables
- partial occlusion
- multi view
- motion capture
- three dimensional
- d objects
- probabilistic model
- random fields
- pairwise
- machine learning