@inproceedings{maaz-etal-2024-video,
title = "Video-{C}hat{GPT}: Towards Detailed Video Understanding via Large Vision and Language Models",
author = "Maaz, Muhammad and
Rasheed, Hanoona and
Khan, Salman and
Khan, Fahad",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.679/",
doi = "10.18653/v1/2024.acl-long.679",
pages = "12585--12602",
abstract = "Conversation agents fueled by Large Language Models (LLMs) are providing a new way to interact with visual data. While there have been initial attempts for image-based conversation models, this work addresses the under-explored field of \textit{video-based conversation} by introducing Video-ChatGPT. It is a multimodal model that merges a video-adapted visual encoder with an LLM. The resulting model is capable of understanding and generating detailed conversations about videos. We introduce a new dataset of 100,000 video-instruction pairs used to train Video-ChatGPT acquired via manual and semi-automated pipeline that is easily scalable and robust to label noise. We also develop a quantitative evaluation framework for video-based dialogue models to objectively analyze the strengths and weaknesses of video-based dialogue models. Code: https://github.com/mbzuai-oryx/Video-ChatGPT."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maaz-etal-2024-video">
<titleInfo>
<title>Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Maaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanoona</namePart>
<namePart type="family">Rasheed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salman</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fahad</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Conversation agents fueled by Large Language Models (LLMs) are providing a new way to interact with visual data. While there have been initial attempts for image-based conversation models, this work addresses the under-explored field of video-based conversation by introducing Video-ChatGPT. It is a multimodal model that merges a video-adapted visual encoder with an LLM. The resulting model is capable of understanding and generating detailed conversations about videos. We introduce a new dataset of 100,000 video-instruction pairs used to train Video-ChatGPT acquired via manual and semi-automated pipeline that is easily scalable and robust to label noise. We also develop a quantitative evaluation framework for video-based dialogue models to objectively analyze the strengths and weaknesses of video-based dialogue models. Code: https://github.com/mbzuai-oryx/Video-ChatGPT.</abstract>
<identifier type="citekey">maaz-etal-2024-video</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.679</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.679/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>12585</start>
<end>12602</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
%A Maaz, Muhammad
%A Rasheed, Hanoona
%A Khan, Salman
%A Khan, Fahad
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F maaz-etal-2024-video
%X Conversation agents fueled by Large Language Models (LLMs) are providing a new way to interact with visual data. While there have been initial attempts for image-based conversation models, this work addresses the under-explored field of video-based conversation by introducing Video-ChatGPT. It is a multimodal model that merges a video-adapted visual encoder with an LLM. The resulting model is capable of understanding and generating detailed conversations about videos. We introduce a new dataset of 100,000 video-instruction pairs used to train Video-ChatGPT acquired via manual and semi-automated pipeline that is easily scalable and robust to label noise. We also develop a quantitative evaluation framework for video-based dialogue models to objectively analyze the strengths and weaknesses of video-based dialogue models. Code: https://github.com/mbzuai-oryx/Video-ChatGPT.
%R 10.18653/v1/2024.acl-long.679
%U https://aclanthology.org/2024.acl-long.679/
%U https://doi.org/10.18653/v1/2024.acl-long.679
%P 12585-12602
Markdown (Informal)
[Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://aclanthology.org/2024.acl-long.679/) (Maaz et al., ACL 2024)
ACL