Exploring Models and Data for Image Question Answering

Code

• github.com/renmengye/imageqa-public
  OfficialIn papernone★ 0
• github.com/moh833/VQA
  none★ 0
• github.com/abhigoyal1997/CS-763-Project
  pytorch★ 0

Abstract

This work aims to address the problem of image-based question-answering (QA) with new models and datasets. In our work, we propose to use neural networks and visual semantic embeddings, without intermediate stages such as object detection and image segmentation, to predict answers to simple questions about images. Our model performs 1.8 times better than the only published results on an existing image QA dataset. We also present a question generation algorithm that converts image descriptions, which are widely available, into QA form. We used this algorithm to produce an order-of-magnitude larger dataset, with more evenly distributed answers. A suite of baseline results on this new dataset are also presented.

Tasks

Benchmark Results

Reproductions