A unified self-supervised model lifts 2D skeletons to 3D, adds skeleton-specific prompts to unify joint sets, and fuses semantic motion encoding to recognize actions from heterogeneous skeleton formats, surpassing prior SOTA on NTU-60, NTU-120, and PKU-MMD II.
Hyperbolic self-paced learning for self-supervised skeleton-based action representations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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
-
Heterogeneous Skeleton-Based Action Representation Learning
A unified self-supervised model lifts 2D skeletons to 3D, adds skeleton-specific prompts to unify joint sets, and fuses semantic motion encoding to recognize actions from heterogeneous skeleton formats, surpassing prior SOTA on NTU-60, NTU-120, and PKU-MMD II.