Self-attention with input-dependent aggregation and soft graph-distance priors outperforms fixed graph convolutions for 2D-to-3D hand pose estimation on FPHA.
3d human pose estima- tion with spatial and temporal transformers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Rethinking Graph Convolution for 2D-to-3D Hand Pose Lifting
Self-attention with input-dependent aggregation and soft graph-distance priors outperforms fixed graph convolutions for 2D-to-3D hand pose estimation on FPHA.