StackOverflowVQA: Stack Overflow Visual Question Answering Dataset

TL;DR

The paper introduces StackOverflowVQA, a novel dataset for visual question answering in software-related contexts, including multiple answers and a baseline model, to advance AI understanding of technical images.

Contribution

It presents the first VQA dataset focused on software questions with images and multiple human-generated answers, along with a baseline model implementation.

Findings

First software-related VQA dataset with multiple answers

Baseline GIT model demonstrates initial performance

Dataset availability for future research

Abstract

In recent years, people have increasingly used AI to help them with their problems by asking questions on different topics. One of these topics can be software-related and programming questions. In this work, we focus on the questions which need the understanding of images in addition to the question itself. We introduce the StackOverflowVQA dataset, which includes questions from StackOverflow that have one or more accompanying images. This is the first VQA dataset that focuses on software-related questions and contains multiple human-generated full-sentence answers. Additionally, we provide a baseline for answering the questions with respect to images in the introduced dataset using the GIT model. All versions of the dataset are available at https://huggingface.co/mirzaei2114.