AI RESEARCH
Less is More: Decoder-Free Masked Modeling for Efficient Skeleton Representation Learning
arXiv CS.CV
•
ArXi:2603.10648v1 Announce Type: new The landscape of skeleton-based action representation learning has evolved from Contrastive Learning (CL) to Masked Auto-Encoder (MAE) architectures. However, each paradigm faces inherent limitations: CL often overlooks fine-grained local details, while MAE is burdened by computationally heavy decoders. Moreover, MAE suffers from severe computational asymmetry -- benefiting from efficient masking during pre-