ImagesTexts

DAQUAR

Introduced in A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input

About this Dataset

DAQUAR (DAtaset for QUestion Answering on Real-world images) is a dataset of human question answer pairs about images.

Source: A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input Image Source: https://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-computing/research/vision-and-language/visual-turing-challenge/

Source: A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input

Dataset Variants

DAQUAR

Papers1

A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input

This work proposes a method for automatically answering questions about images by bringing together recent advances from natural language processing and computer vision by a multi-world approach that represents uncertainty about the perceived world in a bayesian framework.

Tasks

EDIT

Object Detection Question Answering Visual Question Answering (VQA)

Similar Datasets

MNIST

CelebA

GLUE

Statistics

Papers

1

Tasks

0

License

Unknown

Modalities

ImagesTexts