@inproceedings{fu-etal-2023-mulan,
title = "Mulan: A Multi-Level Alignment Model for Video Question Answering",
author = "Fu, Yu and
Cao, Cong and
Yang, Yuling and
Lu, Yuhai and
Yuan, Fangfang and
Wang, Dakui and
Liu, Yanbing",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.364",
doi = "10.18653/v1/2023.findings-emnlp.364",
pages = "5475--5489",
abstract = "Video Question Answering (VideoQA) aims to answer questions about the visual content of a video. Current methods mainly focus on improving joint representations of video and text. However, these methods pay little attention to the fine-grained semantic interaction between video and text. In this paper, we propose Mulan: a Multi-Level Alignment Model for Video Question Answering, which establishes alignment between visual and textual modalities at the object-level, frame-level, and video-level. Specifically, for object-level alignment, we propose a mask-guided visual feature encoding method and a visual-guided text description method to learn fine-grained spatial information. For frame-level alignment, we introduce the use of visual features from individual frames, combined with a caption generator, to learn overall spatial information within the scene. For video-level alignment, we propose an expandable ordinal prompt for textual descriptions, combined with visual features, to learn temporal information. Experimental results show that our method outperforms the state-of-the-art methods, even when utilizing the smallest amount of extra visual-language pre-training data and a reduced number of trainable parameters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2023-mulan">
<titleInfo>
<title>Mulan: A Multi-Level Alignment Model for Video Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cong</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuling</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhai</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fangfang</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dakui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanbing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Video Question Answering (VideoQA) aims to answer questions about the visual content of a video. Current methods mainly focus on improving joint representations of video and text. However, these methods pay little attention to the fine-grained semantic interaction between video and text. In this paper, we propose Mulan: a Multi-Level Alignment Model for Video Question Answering, which establishes alignment between visual and textual modalities at the object-level, frame-level, and video-level. Specifically, for object-level alignment, we propose a mask-guided visual feature encoding method and a visual-guided text description method to learn fine-grained spatial information. For frame-level alignment, we introduce the use of visual features from individual frames, combined with a caption generator, to learn overall spatial information within the scene. For video-level alignment, we propose an expandable ordinal prompt for textual descriptions, combined with visual features, to learn temporal information. Experimental results show that our method outperforms the state-of-the-art methods, even when utilizing the smallest amount of extra visual-language pre-training data and a reduced number of trainable parameters.</abstract>
<identifier type="citekey">fu-etal-2023-mulan</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.364</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.364</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>5475</start>
<end>5489</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mulan: A Multi-Level Alignment Model for Video Question Answering
%A Fu, Yu
%A Cao, Cong
%A Yang, Yuling
%A Lu, Yuhai
%A Yuan, Fangfang
%A Wang, Dakui
%A Liu, Yanbing
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F fu-etal-2023-mulan
%X Video Question Answering (VideoQA) aims to answer questions about the visual content of a video. Current methods mainly focus on improving joint representations of video and text. However, these methods pay little attention to the fine-grained semantic interaction between video and text. In this paper, we propose Mulan: a Multi-Level Alignment Model for Video Question Answering, which establishes alignment between visual and textual modalities at the object-level, frame-level, and video-level. Specifically, for object-level alignment, we propose a mask-guided visual feature encoding method and a visual-guided text description method to learn fine-grained spatial information. For frame-level alignment, we introduce the use of visual features from individual frames, combined with a caption generator, to learn overall spatial information within the scene. For video-level alignment, we propose an expandable ordinal prompt for textual descriptions, combined with visual features, to learn temporal information. Experimental results show that our method outperforms the state-of-the-art methods, even when utilizing the smallest amount of extra visual-language pre-training data and a reduced number of trainable parameters.
%R 10.18653/v1/2023.findings-emnlp.364
%U https://aclanthology.org/2023.findings-emnlp.364
%U https://doi.org/10.18653/v1/2023.findings-emnlp.364
%P 5475-5489
Markdown (Informal)
[Mulan: A Multi-Level Alignment Model for Video Question Answering](https://aclanthology.org/2023.findings-emnlp.364) (Fu et al., Findings 2023)
ACL