# Modulated Self-attention Convolutional Network for VQA

Source: [Modulated Self-attention Convolutional Network for VQA](<https://www.sota2.com/research/paper/68fa66991e209131cea11454>)

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

Data updated: 2025-10-25T21:54:21.040Z

Authors: Jean-Benoit Delbrouck, Antoine Maiorca, Nathan Hubens, St\\'ephane Dupont

Published: 2019-10-08T11:28:38.000Z

## Abstract

As new data-sets for real-world visual reasoning and compositional question answering are emerging, it might be needed to use the visual feature extraction as a end-to-end process during training. This small contribution aims to suggest new ideas to improve the visual processing of traditional convolutional network for visual question answering (VQA). In this paper, we propose to modulate by a linguistic input a CNN augmented with self-attention. We show encouraging relative improvements for future research in this direction.

## 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/1910.03343>)

[PDF](<https://arxiv.org/pdf/1910.03343.pdf>)