2 papers
cs.CV2024
MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion
Lehong Wu, Lilang Lin, Jiahang Zhang +2
Self-supervised learning has proved effective for skeleton-based human action understanding. However, previous works either rely on contrastive learning that suffers false negative…
cs.CV2020
MSL: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition
Lilang Lin, Sijie Song, Wenhan Yan +1
In this paper, we address self-supervised representation learning from human skeletons for action recognition. Previous methods, which usually learn feature presentations from a si…