Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature

TL;DR

This survey reviews recent advances in Visual Question Answering (VQA), analyzing 25 studies and 6 datasets to identify trends, challenges, and future directions in this emerging interdisciplinary field.

Contribution

It provides a comprehensive analysis and comparison of recent VQA research, highlighting common errors, state-of-the-art results, and potential areas for improvement.

Findings

Identified key datasets used in VQA research.

Summarized common challenges and errors in current methods.

Outlined future research directions and potential improvements.

Abstract

Visual Question Answering (VQA) is an emerging area of interest for researches, being a recent problem in natural language processing and image prediction. In this area, an algorithm needs to answer questions about certain images. As of the writing of this survey, 25 recent studies were analyzed. Besides, 6 datasets were analyzed and provided their link to download. In this work, several recent pieces of research in this area were investigated and a deeper analysis and comparison among them were provided, including results, the state-of-the-art, common errors, and possible points of improvement for future researchers.