UAV-VQG: Visual Question Generation Framework on UAV Images
UAV-VQG: Visual Question Generation Framework on UAV Images
复制标题
UAV-VQG：无人机图像上的视觉问题生成框架
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
M. Rahnemoonfar
中科院分区：
文献类型：
--
作者：
Argho Sarkar;M. Rahnemoonfar
视觉问题生成（VQG）是最具挑战性的问题之一，因为它旨在从图像中产生相关的和有意义的问题。由于VQG过程能够生成训练集中不存在的各种问题集，因此可以使用各种模型（例如，视觉问题回答）可以通过评估模型在未知设置中的性能而从该问题生成任务中受益。本文探讨了基于无人机采集图像的视觉问题生成任务。我们强调了问题生成任务的重要作用，并提出了一个基于变分注意力的模型，专注于从图像中创建多样化和有意义的问题。与基线方法相比，我们提出的方法已经证明了创建一组广泛而有意义的问题的能力。
Visual Question Generation (VQG) is one of the most challenging problems since it aims to produce relevant and meaningful questions from images. As the VQG process is able to generate a diverse set of questions that do not exist in the training set, various models (e.g., visual question answering) can be beneficial from this question generation task by evaluating the model’s performance in unknown settings. In this paper, we explored the visual question generation task on images collected by an unmanned aerial vehicle (UAV). We highlight the significant role of the question generation task and present a variational attention-based model that focuses on creating diversified and meaningful questions from images. In comparison to baseline approaches, our presented method has demonstrated the ability to create a broad and meaningful set of questions.