Viquae, a dataset for knowledge-based visual question answering about named entities

HIGHLIGHTS

• who: Paul Lerner and collaborators from the SIGIR u201922, July, u201315, Madrid, Spain have published the research work: ViQuAE, a Dataset for Knowledge-based Visual Question Answering about Named Entities, in the Journal: (JOURNAL) of 21/01/1651
• what: To benchmark this task called KVQAE (Knowledge-based Visual Question the authors provide a dataset of 3.7K questions paired with images. Instead, the work is focused on questions that require knowledge about named entities, such as the boat Queen Elizabeth 2. Instead, the authors aim at building a dataset covering various entity types with a . . .
  

   

  

  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.