Occluded pedestrian-attribute recognition for video sensors using group sparsity

HIGHLIGHTS

• who: Geonu Lee and colleagues from the College of Information Technology, Gachon University, Seongnam , have published the article: Occluded Pedestrian-Attribute Recognition for Video Sensors Using Group Sparsity, in the Journal: Sensors 2022, 22, 6626. of 21/07/2022
• what: To address the uncorrelated attention issue the authors propose a novel temporal-attention module based on is applied across attention weights in correlated attributes. The authors propose a novel method for improving PAR performance in occlusion cases. The authors propose a novel groupsparsity-based temporal attention module. The authors propose a method that simultaneously adjusts . . .
  

   

  

  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.