@inproceedings{nishimura-etal-2024-lighthouse,
title = "Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection",
author = "Nishimura, Taichi and
Nakada, Shota and
Munakata, Hokuto and
Komatsu, Tatsuya",
editor = "Hernandez Farias, Delia Irazu and
Hope, Tom and
Li, Manling",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-demo.6",
pages = "53--60",
abstract = "We propose Lighthouse, a user-friendly library for reproducible video moment retrieval and highlight detection (MR-HD). Although researchers proposed various MR-HD approaches, the research community holds two main issues. The first is a lack of comprehensive and reproducible experiments across various methods, datasets, and video-text features.This is because no unified training and evaluation codebase covers multiple settings. The second is user-unfriendly design. Because previous works use different libraries, researchers set up individual environments. In addition, most works release only the training codes, requiring users to implement the whole inference process of MR-HD. Lighthouse addresses these issues by implementing a unified reproducible codebase that includes six models, three features, and five datasets. In addition, it provides an inference API and web demo to make these methods easily accessible for researchers and developers. Our experiments demonstrate that Lighthouse generally reproduces the reported scores in the reference papers. The code is available at https://github.com/line/lighthouse.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishimura-etal-2024-lighthouse">
<titleInfo>
<title>Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taichi</namePart>
<namePart type="family">Nishimura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shota</namePart>
<namePart type="family">Nakada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hokuto</namePart>
<namePart type="family">Munakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Komatsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Delia</namePart>
<namePart type="given">Irazu</namePart>
<namePart type="family">Hernandez Farias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Hope</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose Lighthouse, a user-friendly library for reproducible video moment retrieval and highlight detection (MR-HD). Although researchers proposed various MR-HD approaches, the research community holds two main issues. The first is a lack of comprehensive and reproducible experiments across various methods, datasets, and video-text features.This is because no unified training and evaluation codebase covers multiple settings. The second is user-unfriendly design. Because previous works use different libraries, researchers set up individual environments. In addition, most works release only the training codes, requiring users to implement the whole inference process of MR-HD. Lighthouse addresses these issues by implementing a unified reproducible codebase that includes six models, three features, and five datasets. In addition, it provides an inference API and web demo to make these methods easily accessible for researchers and developers. Our experiments demonstrate that Lighthouse generally reproduces the reported scores in the reference papers. The code is available at https://github.com/line/lighthouse.</abstract>
<identifier type="citekey">nishimura-etal-2024-lighthouse</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-demo.6</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>53</start>
<end>60</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection
%A Nishimura, Taichi
%A Nakada, Shota
%A Munakata, Hokuto
%A Komatsu, Tatsuya
%Y Hernandez Farias, Delia Irazu
%Y Hope, Tom
%Y Li, Manling
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F nishimura-etal-2024-lighthouse
%X We propose Lighthouse, a user-friendly library for reproducible video moment retrieval and highlight detection (MR-HD). Although researchers proposed various MR-HD approaches, the research community holds two main issues. The first is a lack of comprehensive and reproducible experiments across various methods, datasets, and video-text features.This is because no unified training and evaluation codebase covers multiple settings. The second is user-unfriendly design. Because previous works use different libraries, researchers set up individual environments. In addition, most works release only the training codes, requiring users to implement the whole inference process of MR-HD. Lighthouse addresses these issues by implementing a unified reproducible codebase that includes six models, three features, and five datasets. In addition, it provides an inference API and web demo to make these methods easily accessible for researchers and developers. Our experiments demonstrate that Lighthouse generally reproduces the reported scores in the reference papers. The code is available at https://github.com/line/lighthouse.
%U https://aclanthology.org/2024.emnlp-demo.6
%P 53-60
Markdown (Informal)
[Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection](https://aclanthology.org/2024.emnlp-demo.6) (Nishimura et al., EMNLP 2024)
ACL