Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Feiqi Cao"'
Publikováno v:
Robotics, Vol 12, Iss 4, p 114 (2023)
Visual Question Answering (VQA) models fail catastrophically on questions related to the reading of text-carrying images. However, TextVQA aims to answer questions by understanding the scene texts in an image–question context, such as the brand nam
Externí odkaz:
https://doaj.org/article/7d186ce23f2d4b57bdfa7605718c5654
