Across Images and Graphs for Question Answering

Cross-source query serves as a proxy for scene understanding to support many web applications such as rec-ommendation systems, e-commerce, and e-learning applications. In this paper, we propose SVQA that semantically combines the knowledge from available images and graphs to answer the complex question. To this end, we design a graph-based method to unify various data sources into one representation. We then develop a complex question parse method that utilizes the structure of languages to transform the query into a query graph. A graph query engine that performs the query graph over the unified data source while optimizing the query process. To evaluate the proposed system, we build a vanilla dataset called MVQA and show that the state-of-the-art (SOTA) VQA models fail to perform our task. The comprehensive evaluations show that the proposed SVQA is able to reason implicit relationships over multiple images and external knowledge to correctly answer a complex query. We hope that our first attempt provides researchers with a fresh taste of multimodal data analysis.