@inproceedings{li-etal-2023-three,
title = "Three Stream Based Multi-level Event Contrastive Learning for Text-Video Event Extraction",
author = "Li, Jiaqi and
Zhang, Chuanyi and
Du, Miaozeng and
Min, Dehai and
Chen, Yongrui and
Qi, Guilin",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.103",
doi = "10.18653/v1/2023.emnlp-main.103",
pages = "1666--1676",
abstract = "Text-video based multimodal event extraction refers to identifying event information from the given text-video pairs. Existing methods predominantly utilize video appearance features (VAF) and text sequence features (TSF) as input information. Some of them employ contrastive learning to align VAF with the event types extracted from TSF. However, they disregard the motion representations in videos and the optimization of contrastive objective could be misguided by the background noise from RGB frames. We observe that the same event triggers correspond to similar motion trajectories, which are hardly affected by the background noise. Moviated by this, we propose a Three Stream Multimodal Event Extraction framework (TSEE) that simultaneously utilizes the features of text sequence and video appearance, as well as the motion representations to enhance the event extraction capacity. Firstly, we extract the optical flow features (OFF) as motion representations from videos to incorporate with VAF and TSF. Then we introduce a Multi-level Event Contrastive Learning module to align the embedding space between OFF and event triggers, as well as between event triggers and types. Finally, a Dual Querying Text module is proposed to enhance the interaction between modalities. Experimental results show that TSEE outperforms the state-of-the-art methods, which demonstrates its superiority.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-three">
<titleInfo>
<title>Three Stream Based Multi-level Event Contrastive Learning for Text-Video Event Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaqi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuanyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miaozeng</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dehai</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongrui</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guilin</namePart>
<namePart type="family">Qi</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>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</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>Text-video based multimodal event extraction refers to identifying event information from the given text-video pairs. Existing methods predominantly utilize video appearance features (VAF) and text sequence features (TSF) as input information. Some of them employ contrastive learning to align VAF with the event types extracted from TSF. However, they disregard the motion representations in videos and the optimization of contrastive objective could be misguided by the background noise from RGB frames. We observe that the same event triggers correspond to similar motion trajectories, which are hardly affected by the background noise. Moviated by this, we propose a Three Stream Multimodal Event Extraction framework (TSEE) that simultaneously utilizes the features of text sequence and video appearance, as well as the motion representations to enhance the event extraction capacity. Firstly, we extract the optical flow features (OFF) as motion representations from videos to incorporate with VAF and TSF. Then we introduce a Multi-level Event Contrastive Learning module to align the embedding space between OFF and event triggers, as well as between event triggers and types. Finally, a Dual Querying Text module is proposed to enhance the interaction between modalities. Experimental results show that TSEE outperforms the state-of-the-art methods, which demonstrates its superiority.</abstract>
<identifier type="citekey">li-etal-2023-three</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.103</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.103</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>1666</start>
<end>1676</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Three Stream Based Multi-level Event Contrastive Learning for Text-Video Event Extraction
%A Li, Jiaqi
%A Zhang, Chuanyi
%A Du, Miaozeng
%A Min, Dehai
%A Chen, Yongrui
%A Qi, Guilin
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F li-etal-2023-three
%X Text-video based multimodal event extraction refers to identifying event information from the given text-video pairs. Existing methods predominantly utilize video appearance features (VAF) and text sequence features (TSF) as input information. Some of them employ contrastive learning to align VAF with the event types extracted from TSF. However, they disregard the motion representations in videos and the optimization of contrastive objective could be misguided by the background noise from RGB frames. We observe that the same event triggers correspond to similar motion trajectories, which are hardly affected by the background noise. Moviated by this, we propose a Three Stream Multimodal Event Extraction framework (TSEE) that simultaneously utilizes the features of text sequence and video appearance, as well as the motion representations to enhance the event extraction capacity. Firstly, we extract the optical flow features (OFF) as motion representations from videos to incorporate with VAF and TSF. Then we introduce a Multi-level Event Contrastive Learning module to align the embedding space between OFF and event triggers, as well as between event triggers and types. Finally, a Dual Querying Text module is proposed to enhance the interaction between modalities. Experimental results show that TSEE outperforms the state-of-the-art methods, which demonstrates its superiority.
%R 10.18653/v1/2023.emnlp-main.103
%U https://aclanthology.org/2023.emnlp-main.103
%U https://doi.org/10.18653/v1/2023.emnlp-main.103
%P 1666-1676
Markdown (Informal)
[Three Stream Based Multi-level Event Contrastive Learning for Text-Video Event Extraction](https://aclanthology.org/2023.emnlp-main.103) (Li et al., EMNLP 2023)
ACL