no code implementations • 1 Aug 2023 • Shamanthak Hegde, Soumya Jahagirdar, Shankar Gangisetty
Such a simple, yet effective approach increases the understanding and correlation between the image features and text present in the image, which helps in the better answering of questions.
Optical Character Recognition (OCR) Visual Question Answering (VQA)
no code implementations • 11 Jun 2023 • Charani Alampalle, Shamanthak Hegde, Soumya Jahagirdar, Shankar Gangisetty
To address this issue, we propose a weakly-supervised visual question answer generation method that generates a relevant question-answer pairs for a given input image and associated caption.