We describe a very simple bag-of-words baseline for visual question answering. This baseline concatenates the word features from the question and CNN features from the image to predict the answer. When evaluated on the challenging VQA dataset [2], it shows comparable performance to many recent approaches using recurrent neural networks. To explore the strength and weakness of the trained model, we also provide an interactive web demo and open-source code. .
@article{arxiv.1512.02167,
title = {Simple Baseline for Visual Question Answering},
author = {Bolei Zhou and Yuandong Tian and Sainbayar Sukhbaatar and Arthur Szlam and Rob Fergus},
journal= {arXiv preprint arXiv:1512.02167},
year = {2015}
}
Comments
One comparison method's scores are put into the correct column, and a new experiment of generating attention map is added