@inproceedings{li-etal-2022-mplug,
title = "m{PLUG}: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections",
author = "Li, Chenliang and
Xu, Haiyang and
Tian, Junfeng and
Wang, Wei and
Yan, Ming and
Bi, Bin and
Ye, Jiabo and
Chen, He and
Xu, Guohai and
Cao, Zheng and
Zhang, Ji and
Huang, Songfang and
Huang, Fei and
Zhou, Jingren and
Si, Luo",
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.488",
doi = "10.18653/v1/2022.emnlp-main.488",
pages = "7241--7259",
abstract = "Large-scale pre-trained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks. This paper presents mPLUG, a new vision-language foundation model for both cross-modal understanding and generation. Most existing pre-trained models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment. To address both problems, mPLUG introduces an effective and efficient vision-language architecture with novel cross-modal skip-connections.mPLUG is pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering. mPLUG also demonstrates strong zero-shot transferability on vision-language and video-language tasks. The code and pre-trained models are available at \url{https://github.com/alibaba/AliceMind}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-mplug">
<titleInfo>
<title>mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenliang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junfeng</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Bi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiabo</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guohai</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songfang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingren</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luo</namePart>
<namePart type="family">Si</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>Large-scale pre-trained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks. This paper presents mPLUG, a new vision-language foundation model for both cross-modal understanding and generation. Most existing pre-trained models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment. To address both problems, mPLUG introduces an effective and efficient vision-language architecture with novel cross-modal skip-connections.mPLUG is pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering. mPLUG also demonstrates strong zero-shot transferability on vision-language and video-language tasks. The code and pre-trained models are available at https://github.com/alibaba/AliceMind</abstract>
<identifier type="citekey">li-etal-2022-mplug</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.488</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.488</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>7241</start>
<end>7259</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections
%A Li, Chenliang
%A Xu, Haiyang
%A Tian, Junfeng
%A Wang, Wei
%A Yan, Ming
%A Bi, Bin
%A Ye, Jiabo
%A Chen, He
%A Xu, Guohai
%A Cao, Zheng
%A Zhang, Ji
%A Huang, Songfang
%A Huang, Fei
%A Zhou, Jingren
%A Si, Luo
%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 li-etal-2022-mplug
%X Large-scale pre-trained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks. This paper presents mPLUG, a new vision-language foundation model for both cross-modal understanding and generation. Most existing pre-trained models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment. To address both problems, mPLUG introduces an effective and efficient vision-language architecture with novel cross-modal skip-connections.mPLUG is pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering. mPLUG also demonstrates strong zero-shot transferability on vision-language and video-language tasks. The code and pre-trained models are available at https://github.com/alibaba/AliceMind
%R 10.18653/v1/2022.emnlp-main.488
%U https://aclanthology.org/2022.emnlp-main.488
%U https://doi.org/10.18653/v1/2022.emnlp-main.488
%P 7241-7259
Markdown (Informal)
[mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections](https://aclanthology.org/2022.emnlp-main.488) (Li et al., EMNLP 2022)
ACL
- Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, and Luo Si. 2022. mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7241–7259, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.