Pyramid Graph Transformer pools 2D joints into body parts and regions inside self-attention, reporting lower single-frame 3D pose error with fewer parameters than several baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Pyramid-structured Long-range Dependencies for 3D Human Pose Estimation
Pyramid Graph Transformer pools 2D joints into body parts and regions inside self-attention, reporting lower single-frame 3D pose error with fewer parameters than several baselines.