A spatial-temporal joint density measure detects 'prime joints' that drive contrastive and reconstruction learning, improving self-supervised skeleton action recognition by up to 3.6 points on NTU RGB+D 120.
Asynchronous joint-based tempo- ral pooling for skeleton-based action recognition.IEEE Transactions on Circuits and Systems for Video Technol- ogy, pages 1–1, 2024
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
-
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition
A spatial-temporal joint density measure detects 'prime joints' that drive contrastive and reconstruction learning, improving self-supervised skeleton action recognition by up to 3.6 points on NTU RGB+D 120.