1 code implementation • 1 May 2023 • Yilei Hua, Wenhan Wu, Ce Zheng, Aidong Lu, Mengyuan Liu, Chen Chen, Shiqian Wu
This paper proposes an attention-based contrastive learning framework for skeleton representation learning, called SkeAttnCLR, which integrates local similarity and global features for skeleton-based action representations.
no code implementations • 1 Sep 2022 • Wenhan Wu, Yilei Hua, Ce Zheng, Shiqian Wu, Chen Chen, Aidong Lu
Given the unmasked skeleton sequence, the encoder is fine-tuned for the action recognition task.