An effective spatial relational reasoning networks for visual question answering

HIGHLIGHTS

• who: Xiang Shen and collaborators from the College of Information Engineering, Shanghai Maritime University, Pudong, Shanghai, China, College of have published the article: An effective spatial relational reasoning networks for visual question answering, in the Journal: PLOS ONE of 20/Dec/2021
• what: It requires the model to be able to reason and understand images and text simultaneously. Researchers later introduced an attention mechanism to use image features and the distribution of questions to answers to alleviate noise information and make the model have simple reasoning capabilities. The model described above does not consider the . . .
  

   

  

  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.