@inproceedings{sharma-etal-2018-conceptual,
title = "Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning",
author = "Sharma, Piyush and
Ding, Nan and
Goodman, Sebastian and
Soricut, Radu",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-1238",
doi = "10.18653/v1/P18-1238",
pages = "2556--2565",
abstract = "We present a new dataset of image caption annotations, Conceptual Captions, which contains an order of magnitude more images than the MS-COCO dataset (Lin et al., 2014) and represents a wider variety of both images and image caption styles. We achieve this by extracting and filtering image caption annotations from billions of webpages. We also present quantitative evaluations of a number of image captioning models and show that a model architecture based on Inception-ResNetv2 (Szegedy et al., 2016) for image-feature extraction and Transformer (Vaswani et al., 2017) for sequence modeling achieves the best performance when trained on the Conceptual Captions dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-etal-2018-conceptual">
<titleInfo>
<title>Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piyush</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Goodman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radu</namePart>
<namePart type="family">Soricut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new dataset of image caption annotations, Conceptual Captions, which contains an order of magnitude more images than the MS-COCO dataset (Lin et al., 2014) and represents a wider variety of both images and image caption styles. We achieve this by extracting and filtering image caption annotations from billions of webpages. We also present quantitative evaluations of a number of image captioning models and show that a model architecture based on Inception-ResNetv2 (Szegedy et al., 2016) for image-feature extraction and Transformer (Vaswani et al., 2017) for sequence modeling achieves the best performance when trained on the Conceptual Captions dataset.</abstract>
<identifier type="citekey">sharma-etal-2018-conceptual</identifier>
<identifier type="doi">10.18653/v1/P18-1238</identifier>
<location>
<url>https://aclanthology.org/P18-1238</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>2556</start>
<end>2565</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning
%A Sharma, Piyush
%A Ding, Nan
%A Goodman, Sebastian
%A Soricut, Radu
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F sharma-etal-2018-conceptual
%X We present a new dataset of image caption annotations, Conceptual Captions, which contains an order of magnitude more images than the MS-COCO dataset (Lin et al., 2014) and represents a wider variety of both images and image caption styles. We achieve this by extracting and filtering image caption annotations from billions of webpages. We also present quantitative evaluations of a number of image captioning models and show that a model architecture based on Inception-ResNetv2 (Szegedy et al., 2016) for image-feature extraction and Transformer (Vaswani et al., 2017) for sequence modeling achieves the best performance when trained on the Conceptual Captions dataset.
%R 10.18653/v1/P18-1238
%U https://aclanthology.org/P18-1238
%U https://doi.org/10.18653/v1/P18-1238
%P 2556-2565
Markdown (Informal)
[Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning](https://aclanthology.org/P18-1238) (Sharma et al., ACL 2018)
ACL