Wlit: windows and linear transformer for video action recognition

HIGHLIGHTS

  • who: Ruoxi Sun and collaborators from the Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, China School of Information Science and Technology, ShanghaiTech University, Shanghai, China have published the research: WLiT: Windows and Linear Transformer for Video Action Recognition, in the Journal: Sensors 2023, 23, 1616. of 28/01/2023
  • what: While this approach has a powerful global context modeling capability, its computational complexity grows quadratically with token length, limiting its ability to scale to high-resolution scenarios. The authors propose a complementary framework of Windows and Linear Transformer (WLiT), which ensures the ability . . .

     

    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 ?