# Attention on Attention: Architectures for Visual Question Answering (VQA)

arXiv: https://arxiv.org/abs/1803.07724 · HTML: https://mlsanity.com/paper/1803.07724/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Mar 2018.

## Built on by (most cited first, 4 of 4)

- [Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey](https://mlsanity.com/paper/2411.17558/) (2024)
- [A Comprehensive Survey on Visual Question Answering Datasets and Algorithms](https://mlsanity.com/paper/2411.11150/) (2024)
- [Entity-Focused Dense Passage Retrieval for Outside-Knowledge Visual Question Answering](https://mlsanity.com/paper/2210.10176/) (2022)
- [Improved RAMEN: Towards Domain Generalization for Visual Question Answering](https://mlsanity.com/paper/2109.02370/) (2021)

## Abstract (arXiv)

Visual Question Answering (VQA) is an increasingly popular topic in deep learning research, requiring coordination of natural language processing and computer vision modules into a single architecture. We build upon the model which placed first in the VQA Challenge by developing thirteen new attention mechanisms and introducing a simplified classifier. We performed 300 GPU hours of extensive hyperparameter and architecture searches and were able to achieve an evaluation score of 64.78%, outperforming the existing state-of-the-art single model's validation score of 63.15%.