OTPose: Occlusion-Aware Transformer for Pose Estimation in Sparsely-Labeled Videos.
Kyung-Min JinGun-Hee LeeSeong-Whan LeePublished in: SMC (2022)
Keyphrases
- pose estimation
- human pose
- static images
- video sequences
- human body
- computer vision
- human pose estimation
- d objects
- video frames
- monocular images
- feature points
- position and orientation
- body parts
- pose parameters
- video surveillance
- depth images
- camera pose estimation
- object recognition and pose estimation
- partially occluded
- human actions
- action recognition
- training data
- spatio temporal
- object pose
- image sequences