Context-aware cross-attention for skeleton-based human action recognition

HIGHLIGHTS

  • who: YANBO FAN et al. from the AI Lab, Shenzhen, China , National Engineering Laboratory for Video Technology, Department of Computer Science, Peking University, Beijing, China have published the research work: Context-Aware Cross-Attention for Skeleton-Based Human Action Recognition, in the Journal: (JOURNAL)
  • what: The authors propose a cross-attention module that consists of a self-attention branch a cross-attention branch for skeleton-based action recognition. To facilitate end-to-end training, the authors propose a flexible and lightweight scenario context extraction branch to learn context information from raw RGB video directly. The . . .

     

    Logo ScioWire Beta black

    If you want to have access to all the content you need to log in!

    Thanks :)

    If you don't have an account, you can create one here.

     

Scroll to Top

Add A Knowledge Base Question !

+ = Verify Human or Spambot ?