@inproceedings{wang-etal-2023-fashionklip,
title = "{F}ashion{KLIP}: Enhancing {E}-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph",
author = "Wang, Xiaodan and
Wang, Chengyu and
Li, Lei and
Li, Zhixu and
Chen, Ben and
Jin, Linbo and
Huang, Jun and
Xiao, Yanghua and
Gao, Ming",
editor = "Sitaram, Sunayana and
Beigman Klebanov, Beata and
Williams, Jason D",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-industry.16",
doi = "10.18653/v1/2023.acl-industry.16",
pages = "149--158",
abstract = "Image-text retrieval is a core task in the multi-modal domain, which arises a lot of attention from both research and industry communities. Recently, the booming of visual-language pre-trained (VLP) models has greatly enhanced the performance of cross-modal retrieval. However, the fine-grained interactions between objects from different modalities are far from well-established. This issue becomes more severe in the e-commerce domain, which lacks sufficient training data and fine-grained cross-modal knowledge. To alleviate the problem, this paper proposes a novel e-commerce knowledge-enhanced VLP model FashionKLIP. We first automatically establish a multi-modal conceptual knowledge graph from large-scale e-commerce image-text data, and then inject the prior knowledge into the VLP model to align across modalities at the conceptual level. The experiments conducted on a public benchmark dataset demonstrate that FashionKLIP effectively enhances the performance of e-commerce image-text retrieval upon state-of-the-art VLP models by a large margin. The application of the method in real industrial scenarios also proves the feasibility and efficiency of FashionKLIP.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-fashionklip">
<titleInfo>
<title>FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhixu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linbo</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanghua</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Beigman Klebanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Image-text retrieval is a core task in the multi-modal domain, which arises a lot of attention from both research and industry communities. Recently, the booming of visual-language pre-trained (VLP) models has greatly enhanced the performance of cross-modal retrieval. However, the fine-grained interactions between objects from different modalities are far from well-established. This issue becomes more severe in the e-commerce domain, which lacks sufficient training data and fine-grained cross-modal knowledge. To alleviate the problem, this paper proposes a novel e-commerce knowledge-enhanced VLP model FashionKLIP. We first automatically establish a multi-modal conceptual knowledge graph from large-scale e-commerce image-text data, and then inject the prior knowledge into the VLP model to align across modalities at the conceptual level. The experiments conducted on a public benchmark dataset demonstrate that FashionKLIP effectively enhances the performance of e-commerce image-text retrieval upon state-of-the-art VLP models by a large margin. The application of the method in real industrial scenarios also proves the feasibility and efficiency of FashionKLIP.</abstract>
<identifier type="citekey">wang-etal-2023-fashionklip</identifier>
<identifier type="doi">10.18653/v1/2023.acl-industry.16</identifier>
<location>
<url>https://aclanthology.org/2023.acl-industry.16</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>149</start>
<end>158</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph
%A Wang, Xiaodan
%A Wang, Chengyu
%A Li, Lei
%A Li, Zhixu
%A Chen, Ben
%A Jin, Linbo
%A Huang, Jun
%A Xiao, Yanghua
%A Gao, Ming
%Y Sitaram, Sunayana
%Y Beigman Klebanov, Beata
%Y Williams, Jason D.
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wang-etal-2023-fashionklip
%X Image-text retrieval is a core task in the multi-modal domain, which arises a lot of attention from both research and industry communities. Recently, the booming of visual-language pre-trained (VLP) models has greatly enhanced the performance of cross-modal retrieval. However, the fine-grained interactions between objects from different modalities are far from well-established. This issue becomes more severe in the e-commerce domain, which lacks sufficient training data and fine-grained cross-modal knowledge. To alleviate the problem, this paper proposes a novel e-commerce knowledge-enhanced VLP model FashionKLIP. We first automatically establish a multi-modal conceptual knowledge graph from large-scale e-commerce image-text data, and then inject the prior knowledge into the VLP model to align across modalities at the conceptual level. The experiments conducted on a public benchmark dataset demonstrate that FashionKLIP effectively enhances the performance of e-commerce image-text retrieval upon state-of-the-art VLP models by a large margin. The application of the method in real industrial scenarios also proves the feasibility and efficiency of FashionKLIP.
%R 10.18653/v1/2023.acl-industry.16
%U https://aclanthology.org/2023.acl-industry.16
%U https://doi.org/10.18653/v1/2023.acl-industry.16
%P 149-158
Markdown (Informal)
[FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph](https://aclanthology.org/2023.acl-industry.16) (Wang et al., ACL 2023)
ACL
- Xiaodan Wang, Chengyu Wang, Lei Li, Zhixu Li, Ben Chen, Linbo Jin, Jun Huang, Yanghua Xiao, and Ming Gao. 2023. FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 149–158, Toronto, Canada. Association for Computational Linguistics.