Scene-aware Human Pose Generation using Transformer.
Jieteng YaoJunjie ChenLi NiuBin ShengPublished in: ACM Multimedia (2023)
Keyphrases
- human pose
- depth images
- static images
- pose estimation
- human body
- action recognition
- body parts
- monocular images
- video sequences
- human actions
- human motion
- three dimensional
- single image
- human detection
- image sequences
- dynamic scenes
- latent variables
- low resolution
- depth information
- graph structure
- input image
- low level
- computer vision