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.
Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging problem of articulated human pose estimation in monocular images. The architecture can exploit structural domain constraints such as geometric relationships between body joint locations. We show that joint training of these two model paradigms improves performance and allows us to significantly outperform existing state-of-the-art techniques.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 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.