@inproceedings{yu-etal-2022-ghan,
title = "{GHAN}: Graph-Based Hierarchical Aggregation Network for Text-Video Retrieval",
author = "Yu, Yahan and
Hu, Bojie and
Li, Yu",
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.374/",
doi = "10.18653/v1/2022.emnlp-main.374",
pages = "5547--5557",
abstract = "Text-video retrieval focuses on two aspects: cross-modality interaction and video-language encoding. Currently, the mainstream approach is to train a joint embedding space for multimodal interactions. However, there are structural and semantic differences between text and video, making this approach challenging for fine-grained understanding. In order to solve this, we propose an end-to-end graph-based hierarchical aggregation network for text-video retrieval according to the hierarchy possessed by text and video. We design a token-level weighted network to refine intra-modality representations and construct a graph-based message passing attention network for global-local alignment across modality. We conduct experiments on the public datasets MSR-VTT-9K, MSR-VTT-7K and MSVD, and achieve Recall@1 of 73.0{\%}, 65.6{\%}, and 64.0{\%} , which is 25.7{\%}, 16.5{\%}, and 14.2{\%} better than the current state-of-the-art model."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2022-ghan">
<titleInfo>
<title>GHAN: Graph-Based Hierarchical Aggregation Network for Text-Video Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yahan</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bojie</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Li</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>Text-video retrieval focuses on two aspects: cross-modality interaction and video-language encoding. Currently, the mainstream approach is to train a joint embedding space for multimodal interactions. However, there are structural and semantic differences between text and video, making this approach challenging for fine-grained understanding. In order to solve this, we propose an end-to-end graph-based hierarchical aggregation network for text-video retrieval according to the hierarchy possessed by text and video. We design a token-level weighted network to refine intra-modality representations and construct a graph-based message passing attention network for global-local alignment across modality. We conduct experiments on the public datasets MSR-VTT-9K, MSR-VTT-7K and MSVD, and achieve Recall@1 of 73.0%, 65.6%, and 64.0% , which is 25.7%, 16.5%, and 14.2% better than the current state-of-the-art model.</abstract>
<identifier type="citekey">yu-etal-2022-ghan</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.374</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.374/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>5547</start>
<end>5557</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GHAN: Graph-Based Hierarchical Aggregation Network for Text-Video Retrieval
%A Yu, Yahan
%A Hu, Bojie
%A Li, Yu
%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 yu-etal-2022-ghan
%X Text-video retrieval focuses on two aspects: cross-modality interaction and video-language encoding. Currently, the mainstream approach is to train a joint embedding space for multimodal interactions. However, there are structural and semantic differences between text and video, making this approach challenging for fine-grained understanding. In order to solve this, we propose an end-to-end graph-based hierarchical aggregation network for text-video retrieval according to the hierarchy possessed by text and video. We design a token-level weighted network to refine intra-modality representations and construct a graph-based message passing attention network for global-local alignment across modality. We conduct experiments on the public datasets MSR-VTT-9K, MSR-VTT-7K and MSVD, and achieve Recall@1 of 73.0%, 65.6%, and 64.0% , which is 25.7%, 16.5%, and 14.2% better than the current state-of-the-art model.
%R 10.18653/v1/2022.emnlp-main.374
%U https://aclanthology.org/2022.emnlp-main.374/
%U https://doi.org/10.18653/v1/2022.emnlp-main.374
%P 5547-5557
Markdown (Informal)
[GHAN: Graph-Based Hierarchical Aggregation Network for Text-Video Retrieval](https://aclanthology.org/2022.emnlp-main.374/) (Yu et al., EMNLP 2022)
ACL