Video Question Answering (VideoQA) is a task that requires a model to analyze and understand both the visual content given by the input video and the textual part given by the question, and the interaction between them in order to produce a meaningful answer. In our work we focus on the Egocentric VideoQA task, which exploits first-person videos, because of the importance of such task which can have impact on many different fields, such as those pertaining the social assistance and the industrial training. Recently, an Egocentric VideoQA dataset, called EgoVQA, has been released. Given its small size, models tend to overfit quickly. To alleviate this problem, we propose several augmentation techniques which give us a +5.5% improvement on the final accuracy over the considered baseline.
@article{arxiv.2008.09849,
title = {Data augmentation techniques for the Video Question Answering task},
author = {Alex Falcon and Oswald Lanz and Giuseppe Serra},
journal= {arXiv preprint arXiv:2008.09849},
year = {2020}
}
Comments
16 pages, 5 figures; to be published in Egocentric Perception, Interaction and Computing (EPIC) Workshop Proceedings, at ECCV 2020