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

Source: [Attention on Attention: Architectures for Visual Question Answering (VQA)](<https://www.sota2.com/research/paper/68fa64261e209131cea02e61>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:57:11.341Z

Authors: Jasdeep Singh, Vincent Ying, Alex Nutkiewicz

Published: 2018-03-21T03:05:58.000Z

## Abstract

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%.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1803.07724>)

[PDF](<https://arxiv.org/pdf/1803.07724.pdf>)