# Visual Question Answering Using Semantic Information from Image Descriptions

Source: [Visual Question Answering Using Semantic Information from Image Descriptions](<https://www.sota2.com/research/paper/68fa69b31e209131cea238fb>)

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

Data updated: 2025-10-25T23:06:39.153Z

Authors: Tasmia Tasrin, Md Sultan Al Nahian, Brent Harrison

Published: 2020-04-23T04:35:04.000Z

## Abstract

In this work, we propose a deep neural architecture that uses an attention mechanism which utilizes region based image features, the natural language question asked, and semantic knowledge extracted from the regions of an image to produce open-ended answers for questions asked in a visual question answering (VQA) task. The combination of both region based features and region based textual information about the image bolsters a model to more accurately respond to questions and potentially do so with less required training data. We evaluate our proposed architecture on a VQA task against a strong baseline and show that our method achieves excellent results on this task.

## 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/2004.10966>)

[PDF](<https://arxiv.org/pdf/2004.10966.pdf>)