@inproceedings{gao-etal-2022-caponimage,
title = "{C}ap{O}n{I}mage: Context-driven Dense-Captioning on Image",
author = "Gao, Yiqi and
Hou, Xinglin and
Zhang, Yuanmeng and
Ge, Tiezheng and
Jiang, Yuning and
Wang, Peng",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.226",
doi = "10.18653/v1/2022.emnlp-main.226",
pages = "3449--3465",
abstract = "Existing image captioning systems are dedicated to generating narrative captions for images, which are spatially detached from theimage in presentation. However, texts can also be used as decorations on the image to highlight the key points and increase theattractiveness of images. In this work, we introduce a new taskcalled captioning on image (CapOnImage), which aims to generatedense captions at different locations of the image based on contextual information. To fully exploit the surrounding visual context togenerate the most suitable caption for each location, we propose amulti-modal pre-training model with multi-level pre-training tasksthat progressively learn the correspondence between texts and image locations from easy to difficult. Since the model may generateredundant captions for nearby locations, we further enhance thelocation embedding with neighbor locations as context. For thisnew task, we also introduce a large-scale benchmark called CapOnImage2M, which contains 2.1 million product images, each with anaverage of 4.8 spatially localized captions. Compared with other image captioning model variants, our model achieves the best resultsin both captioning accuracy and diversity aspects.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2022-caponimage">
<titleInfo>
<title>CapOnImage: Context-driven Dense-Captioning on Image</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yiqi</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinglin</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanmeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiezheng</namePart>
<namePart type="family">Ge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuning</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing image captioning systems are dedicated to generating narrative captions for images, which are spatially detached from theimage in presentation. However, texts can also be used as decorations on the image to highlight the key points and increase theattractiveness of images. In this work, we introduce a new taskcalled captioning on image (CapOnImage), which aims to generatedense captions at different locations of the image based on contextual information. To fully exploit the surrounding visual context togenerate the most suitable caption for each location, we propose amulti-modal pre-training model with multi-level pre-training tasksthat progressively learn the correspondence between texts and image locations from easy to difficult. Since the model may generateredundant captions for nearby locations, we further enhance thelocation embedding with neighbor locations as context. For thisnew task, we also introduce a large-scale benchmark called CapOnImage2M, which contains 2.1 million product images, each with anaverage of 4.8 spatially localized captions. Compared with other image captioning model variants, our model achieves the best resultsin both captioning accuracy and diversity aspects.</abstract>
<identifier type="citekey">gao-etal-2022-caponimage</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.226</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.226</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>3449</start>
<end>3465</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CapOnImage: Context-driven Dense-Captioning on Image
%A Gao, Yiqi
%A Hou, Xinglin
%A Zhang, Yuanmeng
%A Ge, Tiezheng
%A Jiang, Yuning
%A Wang, Peng
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F gao-etal-2022-caponimage
%X Existing image captioning systems are dedicated to generating narrative captions for images, which are spatially detached from theimage in presentation. However, texts can also be used as decorations on the image to highlight the key points and increase theattractiveness of images. In this work, we introduce a new taskcalled captioning on image (CapOnImage), which aims to generatedense captions at different locations of the image based on contextual information. To fully exploit the surrounding visual context togenerate the most suitable caption for each location, we propose amulti-modal pre-training model with multi-level pre-training tasksthat progressively learn the correspondence between texts and image locations from easy to difficult. Since the model may generateredundant captions for nearby locations, we further enhance thelocation embedding with neighbor locations as context. For thisnew task, we also introduce a large-scale benchmark called CapOnImage2M, which contains 2.1 million product images, each with anaverage of 4.8 spatially localized captions. Compared with other image captioning model variants, our model achieves the best resultsin both captioning accuracy and diversity aspects.
%R 10.18653/v1/2022.emnlp-main.226
%U https://aclanthology.org/2022.emnlp-main.226
%U https://doi.org/10.18653/v1/2022.emnlp-main.226
%P 3449-3465
Markdown (Informal)
[CapOnImage: Context-driven Dense-Captioning on Image](https://aclanthology.org/2022.emnlp-main.226) (Gao et al., EMNLP 2022)
ACL
- Yiqi Gao, Xinglin Hou, Yuanmeng Zhang, Tiezheng Ge, Yuning Jiang, and Peng Wang. 2022. CapOnImage: Context-driven Dense-Captioning on Image. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3449–3465, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.