Joint angle refinement (JAR), trained on Fourier-synthesized angle sequences and applied with a BiGRU-Attention network, smooths keypoint trajectories and corrects outliers in human pose estimates, outperforming SmoothNet on the paper's test videos.
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
-
Joint angle based learning to refine kinematic human pose estimation
Joint angle refinement (JAR), trained on Fourier-synthesized angle sequences and applied with a BiGRU-Attention network, smooths keypoint trajectories and corrects outliers in human pose estimates, outperforming SmoothNet on the paper's test videos.