@inproceedings{kafle-etal-2017-data,
title = "Data Augmentation for Visual Question Answering",
author = "Kafle, Kushal and
Yousefhussien, Mohammed and
Kanan, Christopher",
editor = "Alonso, Jose M. and
Bugar{\'\i}n, Alberto and
Reiter, Ehud",
booktitle = "Proceedings of the 10th International Conference on Natural Language Generation",
month = sep,
year = "2017",
address = "Santiago de Compostela, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-3529",
doi = "10.18653/v1/W17-3529",
pages = "198--202",
abstract = "Data augmentation is widely used to train deep neural networks for image classification tasks. Simply flipping images can help learning tremendously by increasing the number of training images by a factor of two. However, little work has been done studying data augmentation in natural language processing. Here, we describe two methods for data augmentation for Visual Question Answering (VQA). The first uses existing semantic annotations to generate new questions. The second method is a generative approach using recurrent neural networks. Experiments show that the proposed data augmentation improves performance of both baseline and state-of-the-art VQA algorithms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kafle-etal-2017-data">
<titleInfo>
<title>Data Augmentation for Visual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kushal</namePart>
<namePart type="family">Kafle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Yousefhussien</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Kanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Alonso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Bugarín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santiago de Compostela, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data augmentation is widely used to train deep neural networks for image classification tasks. Simply flipping images can help learning tremendously by increasing the number of training images by a factor of two. However, little work has been done studying data augmentation in natural language processing. Here, we describe two methods for data augmentation for Visual Question Answering (VQA). The first uses existing semantic annotations to generate new questions. The second method is a generative approach using recurrent neural networks. Experiments show that the proposed data augmentation improves performance of both baseline and state-of-the-art VQA algorithms.</abstract>
<identifier type="citekey">kafle-etal-2017-data</identifier>
<identifier type="doi">10.18653/v1/W17-3529</identifier>
<location>
<url>https://aclanthology.org/W17-3529</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>198</start>
<end>202</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Augmentation for Visual Question Answering
%A Kafle, Kushal
%A Yousefhussien, Mohammed
%A Kanan, Christopher
%Y Alonso, Jose M.
%Y Bugarín, Alberto
%Y Reiter, Ehud
%S Proceedings of the 10th International Conference on Natural Language Generation
%D 2017
%8 September
%I Association for Computational Linguistics
%C Santiago de Compostela, Spain
%F kafle-etal-2017-data
%X Data augmentation is widely used to train deep neural networks for image classification tasks. Simply flipping images can help learning tremendously by increasing the number of training images by a factor of two. However, little work has been done studying data augmentation in natural language processing. Here, we describe two methods for data augmentation for Visual Question Answering (VQA). The first uses existing semantic annotations to generate new questions. The second method is a generative approach using recurrent neural networks. Experiments show that the proposed data augmentation improves performance of both baseline and state-of-the-art VQA algorithms.
%R 10.18653/v1/W17-3529
%U https://aclanthology.org/W17-3529
%U https://doi.org/10.18653/v1/W17-3529
%P 198-202
Markdown (Informal)
[Data Augmentation for Visual Question Answering](https://aclanthology.org/W17-3529) (Kafle et al., INLG 2017)
ACL
- Kushal Kafle, Mohammed Yousefhussien, and Christopher Kanan. 2017. Data Augmentation for Visual Question Answering. In Proceedings of the 10th International Conference on Natural Language Generation, pages 198–202, Santiago de Compostela, Spain. Association for Computational Linguistics.