Simple Baseline for Visual Question Answering
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.

Simple Baseline for Visual Question Answering

We descrive a very simple bag-of-words baseline for visual question answering. The description of the baseline is in the arXiv paper The code is developed by Bolei Zhou and Yuandong Tian.


Demo is available at

To train the model using the code, the following data of the VQA dataset are needed:

The pre-trained model used in the paper is at It has 55.89 on the Open-Ended and 61.69 on Multiple-Choice for the test-standard of COCO VQA dataset.

Contact Bolei Zhou ( if you have any questions.

Please cite our arXiv note if you use our code:

B. Zhou, Y. Tian, S. Suhkbaatar, A. Szlam, R. Fergus. Simple Baseline for Visual Question Answering. arXiv:1512.02167