Recent Advances in Video Question Answering: A Review of Datasets and Methods

TL;DR

This survey reviews recent datasets and methods in Video Question Answering, highlighting its role in retrieving and interpreting complex visual information from videos, and noting the lack of prior comprehensive reviews.

Contribution

It provides the first comprehensive review of VQA datasets and methods, summarizing recent advances and identifying gaps in the field.

Findings

VQA enables detailed temporal and spatial video understanding.

Several new datasets have been introduced for VQA.

Methodological advancements have improved VQA performance.

Abstract

Video Question Answering (VQA) is a recent emerging challenging task in the field of Computer Vision. Several visual information retrieval techniques like Video Captioning/Description and Video-guided Machine Translation have preceded the task of VQA. VQA helps to retrieve temporal and spatial information from the video scenes and interpret it. In this survey, we review a number of methods and datasets for the task of VQA. To the best of our knowledge, no previous survey has been conducted for the VQA task.