Think Visually: Question Answering through Virtual Imagery
arXiv:1805.11025
Abstract
In this paper, we study the problem of geometric reasoning in the context of question-answering. We introduce Dynamic Spatial Memory Network (DSMN), a new deep network architecture designed for answering questions that admit latent visual representations. DSMN 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.
arXiv commentAccepted in ACL 2018
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Generative Adversarial Text to Image Synthesis
- Hierarchical Question-Image Co-Attention for Visual Question Answering
- VQA: Visual Question Answering
- DRAW: A Recurrent Neural Network For Image Generation
- Dynamic Memory Networks for Visual and Textual Question Answering
- Don't Just Listen, Use Your Imagination: Leveraging Visual Common Sense for Non-Visual Tasks
- Dialog state tracking, a machine reading approach using Memory Network