Simple Baseline for Visual Question Answering

Bolei Zhou, Yuandong Tian, Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus
12/7/2015
cs.CVcs.CL

Official code: zhoubolei/VQAbaseline (184 stars, last commit 2016-12-21).

Abstract

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. .

View on arXivView PDF

Code Implementations(1)

zhoubolei/VQAbaselineOfficial100%

Simple Baseline for Visual Question Answering

18437LuaDec 3, 20159 years ago

Similar Papers

OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese

85% match1 repo62023

Focal Visual-Text Attention for Visual Question Answering

85% match1 repo332018

LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering

85% match1 repo82020

GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering

85% match1 repo5092019

VQA Therapy: Exploring Answer Differences by Visually Grounding Answers

84% match2023

Exploring Models and Data for Image Question Answering

84% match1 repo822015

Cite this paper

@article{zhou2015simple,
  title  = {Simple Baseline for Visual Question Answering},
  author = {Bolei Zhou and Yuandong Tian and Sainbayar Sukhbaatar and Arthur Szlam and Rob Fergus},
  year   = {2015},
  eprint = {1512.02167},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1512.02167}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1512.02167.svg)](https://codeofpaper.com/paper/1512.02167)

Discussion