@inproceedings{le-etal-2022-vgnmn,
title = "{VGNMN}: Video-grounded Neural Module Networks for Video-Grounded Dialogue Systems",
author = "Le, Hung and
Chen, Nancy and
Hoi, Steven",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.247",
doi = "10.18653/v1/2022.naacl-main.247",
pages = "3377--3393",
abstract = "Neural module networks (NMN) have achieved success in image-grounded tasks such as Visual Question Answering (VQA) on synthetic images. However, very limited work on NMN has been studied in the video-grounded dialogue tasks. These tasks extend the complexity of traditional visual tasks with the additional visual temporal variance and language cross-turn dependencies. Motivated by recent NMN approaches on image-grounded tasks, we introduce Video-grounded Neural Module Network (VGNMN) to model the information retrieval process in video-grounded language tasks as a pipeline of neural modules. VGNMN first decomposes all language components in dialogues to explicitly resolve any entity references and detect corresponding action-based inputs from the question. The detected entities and actions are used as parameters to instantiate neural module networks and extract visual cues from the video. Our experiments show that VGNMN can achieve promising performance on a challenging video-grounded dialogue benchmark as well as a video QA benchmark.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-etal-2022-vgnmn">
<titleInfo>
<title>VGNMN: Video-grounded Neural Module Networks for Video-Grounded Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Hoi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural module networks (NMN) have achieved success in image-grounded tasks such as Visual Question Answering (VQA) on synthetic images. However, very limited work on NMN has been studied in the video-grounded dialogue tasks. These tasks extend the complexity of traditional visual tasks with the additional visual temporal variance and language cross-turn dependencies. Motivated by recent NMN approaches on image-grounded tasks, we introduce Video-grounded Neural Module Network (VGNMN) to model the information retrieval process in video-grounded language tasks as a pipeline of neural modules. VGNMN first decomposes all language components in dialogues to explicitly resolve any entity references and detect corresponding action-based inputs from the question. The detected entities and actions are used as parameters to instantiate neural module networks and extract visual cues from the video. Our experiments show that VGNMN can achieve promising performance on a challenging video-grounded dialogue benchmark as well as a video QA benchmark.</abstract>
<identifier type="citekey">le-etal-2022-vgnmn</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.247</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.247</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>3377</start>
<end>3393</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VGNMN: Video-grounded Neural Module Networks for Video-Grounded Dialogue Systems
%A Le, Hung
%A Chen, Nancy
%A Hoi, Steven
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F le-etal-2022-vgnmn
%X Neural module networks (NMN) have achieved success in image-grounded tasks such as Visual Question Answering (VQA) on synthetic images. However, very limited work on NMN has been studied in the video-grounded dialogue tasks. These tasks extend the complexity of traditional visual tasks with the additional visual temporal variance and language cross-turn dependencies. Motivated by recent NMN approaches on image-grounded tasks, we introduce Video-grounded Neural Module Network (VGNMN) to model the information retrieval process in video-grounded language tasks as a pipeline of neural modules. VGNMN first decomposes all language components in dialogues to explicitly resolve any entity references and detect corresponding action-based inputs from the question. The detected entities and actions are used as parameters to instantiate neural module networks and extract visual cues from the video. Our experiments show that VGNMN can achieve promising performance on a challenging video-grounded dialogue benchmark as well as a video QA benchmark.
%R 10.18653/v1/2022.naacl-main.247
%U https://aclanthology.org/2022.naacl-main.247
%U https://doi.org/10.18653/v1/2022.naacl-main.247
%P 3377-3393
Markdown (Informal)
[VGNMN: Video-grounded Neural Module Networks for Video-Grounded Dialogue Systems](https://aclanthology.org/2022.naacl-main.247) (Le et al., NAACL 2022)
ACL