@inproceedings{yan-etal-2021-l2c,
title = "{L}2{C}: Describing Visual Differences Needs Semantic Understanding of Individuals",
author = "Yan, An and
Wang, Xin and
Fu, Tsu-Jui and
Wang, William Yang",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.196",
doi = "10.18653/v1/2021.eacl-main.196",
pages = "2315--2320",
abstract = "Recent advances in language and vision push forward the research of captioning a single image to describing visual differences between image pairs. Suppose there are two images, I{\_}1 and I{\_}2, and the task is to generate a description W{\_}1,2 comparing them, existing methods directly model I{\_}1, I{\_}2 -{\textgreater} W{\_}1,2 mapping without the semantic understanding of individuals. In this paper, we introduce a Learning-to-Compare (L2C) model, which learns to understand the semantic structures of these two images and compare them while learning to describe each one. We demonstrate that L2C benefits from a comparison between explicit semantic representations and single-image captions, and generalizes better on the new testing image pairs. It outperforms the baseline on both automatic evaluation and human evaluation for the Birds-to-Words dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2021-l2c">
<titleInfo>
<title>L2C: Describing Visual Differences Needs Semantic Understanding of Individuals</title>
</titleInfo>
<name type="personal">
<namePart type="given">An</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsu-Jui</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">Yang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-apr</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in language and vision push forward the research of captioning a single image to describing visual differences between image pairs. Suppose there are two images, I_1 and I_2, and the task is to generate a description W_1,2 comparing them, existing methods directly model I_1, I_2 -\textgreater W_1,2 mapping without the semantic understanding of individuals. In this paper, we introduce a Learning-to-Compare (L2C) model, which learns to understand the semantic structures of these two images and compare them while learning to describe each one. We demonstrate that L2C benefits from a comparison between explicit semantic representations and single-image captions, and generalizes better on the new testing image pairs. It outperforms the baseline on both automatic evaluation and human evaluation for the Birds-to-Words dataset.</abstract>
<identifier type="citekey">yan-etal-2021-l2c</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.196</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.196</url>
</location>
<part>
<date>2021-apr</date>
<extent unit="page">
<start>2315</start>
<end>2320</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T L2C: Describing Visual Differences Needs Semantic Understanding of Individuals
%A Yan, An
%A Wang, Xin
%A Fu, Tsu-Jui
%A Wang, William Yang
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 apr
%I Association for Computational Linguistics
%C Online
%F yan-etal-2021-l2c
%X Recent advances in language and vision push forward the research of captioning a single image to describing visual differences between image pairs. Suppose there are two images, I_1 and I_2, and the task is to generate a description W_1,2 comparing them, existing methods directly model I_1, I_2 -\textgreater W_1,2 mapping without the semantic understanding of individuals. In this paper, we introduce a Learning-to-Compare (L2C) model, which learns to understand the semantic structures of these two images and compare them while learning to describe each one. We demonstrate that L2C benefits from a comparison between explicit semantic representations and single-image captions, and generalizes better on the new testing image pairs. It outperforms the baseline on both automatic evaluation and human evaluation for the Birds-to-Words dataset.
%R 10.18653/v1/2021.eacl-main.196
%U https://aclanthology.org/2021.eacl-main.196
%U https://doi.org/10.18653/v1/2021.eacl-main.196
%P 2315-2320
Markdown (Informal)
[L2C: Describing Visual Differences Needs Semantic Understanding of Individuals](https://aclanthology.org/2021.eacl-main.196) (Yan et al., EACL 2021)
ACL