VQABQ: Visual Question Answering by Basic Questions

• DOI: 10.48550/arxiv.1703.06492
• Publication Date: 2017-01-01
• Authors: Jia-Hong Huang; Modar Alfadly; Bernard Ghanem
• Keywords: Questions and answers; Lasso

Taking an image and question as the input of our method, it can output text-based answer query about given image, so called Visual Question Answering (VQA). There are two main modules in algorithm. Given a natural language first module takes then outputs basic questions question. The second question, these We formulate generation problem LASSO optimization problem, also propose criterion how to exploit help Our method is evaluated on challenging VQA dataset yields state-of-the-art accuracy, 60.34% open-ended task.