@inproceedings{wang-etal-2025-dream,
title = "{DREAM}: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models",
author = "Wang, Yimu and
Yuan, Shuai and
Xue, Bo and
Jian, Xiangru and
Pang, Wei and
Wang, Mushi and
Yu, Ning",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.156/",
doi = "10.18653/v1/2025.naacl-long.156",
pages = "3037--3056",
ISBN = "979-8-89176-189-6",
abstract = "Recent progress in video-text retrieval has been driven largely by advancements in model architectures and training strategies. However, the representation learning capabilities of video-text retrieval models remain constrained by low-quality and limited training data annotations. To address this issue, we present a novel Vi\textbf{d}eo-Text \textbf{R}etrieval Paradigm with R\textbf{e}levance-based \textbf{A}ug\textbf{m}entation, namely dReAm, which enhances video and text data using large foundation models to learn more generalized features. Specifically, we first adopt a simple augmentation method, which generates self-similar data by randomly duplicating or dropping subwords and frames. In addition, inspired by the recent advancement in visual and language generative models, we propose a more robust augmentation method through textual paraphrasing and video stylization using large language models (LLMs) and visual generative models (VGMs). To further enrich video and text information, we propose a relevance-based augmentation method, where LLMs and VGMs generate and integrate new relevant information into the original data. Leveraging this enriched data, extensive experiments on several video-text retrieval benchmarks demonstrate the superiority of dReAm over existing methods. Code will be available upon acceptance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-dream">
<titleInfo>
<title>DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangru</namePart>
<namePart type="family">Jian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Pang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mushi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ning</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Recent progress in video-text retrieval has been driven largely by advancements in model architectures and training strategies. However, the representation learning capabilities of video-text retrieval models remain constrained by low-quality and limited training data annotations. To address this issue, we present a novel Video-Text Retrieval Paradigm with Relevance-based Augmentation, namely dReAm, which enhances video and text data using large foundation models to learn more generalized features. Specifically, we first adopt a simple augmentation method, which generates self-similar data by randomly duplicating or dropping subwords and frames. In addition, inspired by the recent advancement in visual and language generative models, we propose a more robust augmentation method through textual paraphrasing and video stylization using large language models (LLMs) and visual generative models (VGMs). To further enrich video and text information, we propose a relevance-based augmentation method, where LLMs and VGMs generate and integrate new relevant information into the original data. Leveraging this enriched data, extensive experiments on several video-text retrieval benchmarks demonstrate the superiority of dReAm over existing methods. Code will be available upon acceptance.</abstract>
<identifier type="citekey">wang-etal-2025-dream</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.156</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.156/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>3037</start>
<end>3056</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models
%A Wang, Yimu
%A Yuan, Shuai
%A Xue, Bo
%A Jian, Xiangru
%A Pang, Wei
%A Wang, Mushi
%A Yu, Ning
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F wang-etal-2025-dream
%X Recent progress in video-text retrieval has been driven largely by advancements in model architectures and training strategies. However, the representation learning capabilities of video-text retrieval models remain constrained by low-quality and limited training data annotations. To address this issue, we present a novel Video-Text Retrieval Paradigm with Relevance-based Augmentation, namely dReAm, which enhances video and text data using large foundation models to learn more generalized features. Specifically, we first adopt a simple augmentation method, which generates self-similar data by randomly duplicating or dropping subwords and frames. In addition, inspired by the recent advancement in visual and language generative models, we propose a more robust augmentation method through textual paraphrasing and video stylization using large language models (LLMs) and visual generative models (VGMs). To further enrich video and text information, we propose a relevance-based augmentation method, where LLMs and VGMs generate and integrate new relevant information into the original data. Leveraging this enriched data, extensive experiments on several video-text retrieval benchmarks demonstrate the superiority of dReAm over existing methods. Code will be available upon acceptance.
%R 10.18653/v1/2025.naacl-long.156
%U https://aclanthology.org/2025.naacl-long.156/
%U https://doi.org/10.18653/v1/2025.naacl-long.156
%P 3037-3056
Markdown (Informal)
[DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models](https://aclanthology.org/2025.naacl-long.156/) (Wang et al., NAACL 2025)
ACL