Think Visually: Question Answering through Virtual Imagery
Think Visually: Question Answering through Virtual Imagery
复制标题
DOI：
10.18653/v1/p18-1242
复制
发表时间：
2018-05
期刊：
影响因子：
--
通讯作者：
Ankit Goyal;Jian Wang;Jia Deng
中科院分区：
文献类型：
--
作者：
Ankit Goyal;Jian Wang;Jia Deng
本文研究了问答环境下的几何推理（视觉推理的一种形式）问题。我们介绍了动态空间记忆网络（DSMN），这是一种新的深度网络架构，专门用于回答承认潜在视觉表征的问题，并学习在这些表征上生成和推理。此外，我们提出了FloorPlanQA和ShapeIntersection两个综合基准来评估QA系统的几何推理能力。实验结果验证了该方法在视觉思维任务中的有效性。
In this paper, we study the problem of geometric reasoning (a form of visual reasoning) in the context of question-answering. We introduce Dynamic Spatial Memory Network (DSMN), a new deep network architecture that specializes in answering questions that admit latent visual representations, and learns to generate and reason over such representations. Further, we propose two synthetic benchmarks, FloorPlanQA and ShapeIntersection, to evaluate the geometric reasoning capability of QA systems. Experimental results validate the effectiveness of our proposed DSMN for visual thinking tasks.