Joint cross-consistency learning and multi-feature fusion for person re-identification

HIGHLIGHTS

• who: Danping Ren et al. from the School of Information and Electrical Engineering, Hebei University of Engineering, Handan, China have published the Article: Joint Cross-Consistency Learning and Multi-Feature Fusion for Person Re-Identification, in the Journal: Sensors 2022, 9387 of /2022/
• what: The attention mechanism and the mixed pooling module were first embedded in the residual network so that the model adaptively focuses on the more valid information in the images. The model was fine-tuned in the multi-feature fusion module, and the fused multilevel features were used to match the similarity . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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