Speech2Video Synthesis with 3D Skeleton Regularization and Expressive Body Poses.
Miao LiaoSibo ZhangPeng WangHao ZhuXinxin ZuoRuigang YangPublished in: ACCV (5) (2020)
Keyphrases
- human actions
- video sequences
- human body tracking
- multimedia
- video frames
- video data
- body pose
- action recognition
- body parts
- markov random field
- generative model
- pose estimation
- human pose estimation
- spatial and temporal
- human activities
- image sequences
- computer vision
- globally optimal
- space time
- human body
- low dimensional