Pith. sign in

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 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Heterogeneous Skeleton-Based Action Representation Learning

cs.CV · 2025-06-04 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Heterogeneous Skeleton-Based Action Representation Learning cs.CV · 2025-06-04 · conditional · none · ref 8

    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.