SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
Skeleton sequence representation learning has shown great advantages for action recognition due to its promising ability to model human joints and topology. However, the current methods usually require sufficient labeled data for training computationally expensive models. Moreover, these methods ignore how to utilize the fine-grained dependencies among different skeleton joints …