VQA: Visual Question Answering

Code

• github.com/vipulgupta1011/swapmix
  pytorch★ 20
• github.com/mkhalil1998/EC601_Group_Project
  pytorch★ 2
• github.com/mokhalid-dev/Attention-based-VQA-model
  pytorch★ 0
• github.com/ramprs/grad-cam
  torch★ 0
• github.com/yanxinyan1/yxy
  pytorch★ 0
• github.com/moh833/VQA
  none★ 0
• github.com/SatyamGaba/vqa
  pytorch★ 0
• github.com/SatyamGaba/visual_question_answering
  pytorch★ 0
• github.com/tbmoon/basic_vqa
  pytorch★ 0
• github.com/SuchismitaSahu1993/VQA-System
  none★ 0

Abstract

We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural language answer. Mirroring real-world scenarios, such as helping the visually impaired, both the questions and answers are open-ended. Visual questions selectively target different areas of an image, including background details and underlying context. As a result, a system that succeeds at VQA typically needs a more detailed understanding of the image and complex reasoning than a system producing generic image captions. Moreover, VQA is amenable to automatic evaluation, since many open-ended answers contain only a few words or a closed set of answers that can be provided in a multiple-choice format. We provide a dataset containing ~0.25M images, ~0.76M questions, and ~10M answers (www.visualqa.org), and discuss the information it provides. Numerous baselines and methods for VQA are provided and compared with human performance. Our VQA demo is available on CloudCV (http://cloudcv.org/vqa).

Tasks

Benchmark Results

Reproductions