Visual Question Answering: A Survey of Methods and Datasets

TL;DR

This survey reviews current methods and datasets in Visual Question Answering, highlighting approaches that combine visual and textual reasoning, and discusses future directions involving knowledge bases and NLP models.

Contribution

It provides a comprehensive classification of VQA methods and an in-depth review of datasets, emphasizing the integration of structured knowledge and reasoning capabilities.

Findings

Comparison of neural network-based approaches

Analysis of datasets including Visual Genome

Discussion on future research directions

Abstract

Visual Question Answering (VQA) is a challenging task that has received increasing attention from both the computer vision and the natural language processing communities. Given an image and a question in natural language, it requires reasoning over visual elements of the image and general knowledge to infer the correct answer. In the first part of this survey, we examine the state of the art by comparing modern approaches to the problem. We classify methods by their mechanism to connect the visual and textual modalities. In particular, we examine the common approach of combining convolutional and recurrent neural networks to map images and questions to a common feature space. We also discuss memory-augmented and modular architectures that interface with structured knowledge bases. In the second part of this survey, we review the datasets available for training and evaluating VQA systems. The various datatsets contain questions at different levels of complexity, which require different capabilities and types of reasoning. We examine in depth the question/answer pairs from the Visual Genome project, and evaluate the relevance of the structured annotations of images with scene graphs for VQA. Finally, we discuss promising future directions for the field, in particular the connection to structured knowledge bases and the use of natural language processing models.