Lightweight smoke recognition based on deep convolution and self-attention

HIGHLIGHTS

• who: Yang Zhao et al. from the School of Computer Science and Technology, Shenyang University of Chemical Technology, Shenyang, China have published the paper: Lightweight Smoke Recognition Based on Deep Convolution and Self-Attention, in the Journal: Mathematical Problems in Engineering of 21/08/2022
• what: Background the authors propose a novel smoke recognition network that combines convolutional networks (CNN) and selfattention. To use self-attention to expand the network's attention region for spatial information without introducing too much extra computational cost, the authors design Skip Block. The authors design DCT-GAP to fuse . . .
  

   

  

  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.