PoseGTAC: Graph Transformer Encoder-Decoder with Atrous Convolution for 3D Human Pose Estimation.
Yiran ZhuXing XuFumin ShenYanli JiLianli GaoHeng Tao ShenPublished in: IJCAI (2021)
Keyphrases
- video codec
- low complexity
- decoding process
- distributed video coding
- error control
- noisy channel
- rate distortion
- successive approximation
- mpeg avc
- directed graph
- motion estimation
- distributed source coding
- image processing
- graph structure
- rate allocation
- wyner ziv
- wyner ziv video coding
- bit rate
- weighted graph
- turbo codes
- video coding
- transform domain
- fuzzy logic
- pixel domain
- image coding
- motion compensated prediction
- inter frame
- temporal correlation
- bit budget
- compressive sensing
- video compression