A Comparative Study on Visual Question Answering Using CNN, LSTM, Vision Transformer, and Bert.

Title A Comparative Study on Visual Question Answering Using CNN, LSTM, Vision Transformer, and Bert.
Authors Ashfaq Uddin Ahmed,S M Gazzali Arafat Nishan,Tasfia Tabassum
Supervisor Dr. Mohammad Ashrafuzzaman Khan
Semester Summer, 2022