Authors: Yash Dixit
Description: Sequence to Sequence Architecture with custom scoring function
Blog Article - https://yashcdixit1998.medium.com/document-visual-question-answering-system-a-serviceable-case-study
I have kept my learning and code open source - Please refer 'Source Code' to go through my code and my research in depth.
Reference Paper 1 -- Kelvin Xu, Jimmy Lei Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard S. Zemel, Yoshua Bengio :: Show, Attend and Tell: Neural Image Caption Generation with Visual Attention.
Reference Paper 2 -- Dzmitry Bahdanau, KyungHyun Cho, Yoshua Bengio :: Neural Machine Translation by jointly learning to align and translate.