Introduces A4Mer for self-supervised hierarchical learning of Action Atoms and Motifs from pose sequences via masked prediction, plus the AMD dataset with foot-mounted camera annotations, to aid action recognition, motion prediction, and interpolation.
On the Continuity of Rotation Representations in Neural Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements
Introduces A4Mer for self-supervised hierarchical learning of Action Atoms and Motifs from pose sequences via masked prediction, plus the AMD dataset with foot-mounted camera annotations, to aid action recognition, motion prediction, and interpolation.