St-tnet: an spatio-temporal joint transformer network for csi feedback in fdd-mimo systems

HIGHLIGHTS

• What: Although downlink CSI needs to be estimated accurately and timely and plays a key role in practical applications , the work in this paper focuses on providing a more accurate feedback method. The authors propose a Spatio-temporal joint Transformer decoder (abbreviated as ST-T), and a new lightweight convolutional transformer network (abbreviated as ST-TNet) on top of the existing feature extraction CNN encoder. The authors design a spatial-temporal joint Transformer decoder for recovering S as Ĥa: Ĥa=fd (S) the authors introduce the CBAM module . (17) Using multi-head attention, the model . . .
  

   

  

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

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

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