@inproceedings{devaraj-etal-2024-diving,
title = "Diving Deep into the Motion Representation of Video-Text Models",
author = "Devaraj, Chinmaya and
Fermuller, Cornelia and
Aloimonos, Yiannis",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.747",
pages = "12575--12584",
abstract = "Videos are more informative than images becausethey capture the dynamics of the scene.By representing motion in videos, we can capturedynamic activities. In this work, we introduceGPT-4 generated motion descriptions thatcapture fine-grained motion descriptions of activitiesand apply them to three action datasets.We evaluated several video-text models on thetask of retrieval of motion descriptions. Wefound that they fall far behind human expertperformance on two action datasets, raisingthe question of whether video-text models understandmotion in videos. To address it, weintroduce a method of improving motion understandingin video-text models by utilizingmotion descriptions. This method proves tobe effective on two action datasets for the motiondescription retrieval task. The results drawattention to the need for quality captions involvingfine-grained motion information in existingdatasets and demonstrate the effectiveness ofthe proposed pipeline in understanding finegrainedmotion during video-text retrieval.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="devaraj-etal-2024-diving">
<titleInfo>
<title>Diving Deep into the Motion Representation of Video-Text Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chinmaya</namePart>
<namePart type="family">Devaraj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cornelia</namePart>
<namePart type="family">Fermuller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiannis</namePart>
<namePart type="family">Aloimonos</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>Findings of the Association for Computational Linguistics ACL 2024</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 and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Videos are more informative than images becausethey capture the dynamics of the scene.By representing motion in videos, we can capturedynamic activities. In this work, we introduceGPT-4 generated motion descriptions thatcapture fine-grained motion descriptions of activitiesand apply them to three action datasets.We evaluated several video-text models on thetask of retrieval of motion descriptions. Wefound that they fall far behind human expertperformance on two action datasets, raisingthe question of whether video-text models understandmotion in videos. To address it, weintroduce a method of improving motion understandingin video-text models by utilizingmotion descriptions. This method proves tobe effective on two action datasets for the motiondescription retrieval task. The results drawattention to the need for quality captions involvingfine-grained motion information in existingdatasets and demonstrate the effectiveness ofthe proposed pipeline in understanding finegrainedmotion during video-text retrieval.</abstract>
<identifier type="citekey">devaraj-etal-2024-diving</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.747</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>12575</start>
<end>12584</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Diving Deep into the Motion Representation of Video-Text Models
%A Devaraj, Chinmaya
%A Fermuller, Cornelia
%A Aloimonos, Yiannis
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F devaraj-etal-2024-diving
%X Videos are more informative than images becausethey capture the dynamics of the scene.By representing motion in videos, we can capturedynamic activities. In this work, we introduceGPT-4 generated motion descriptions thatcapture fine-grained motion descriptions of activitiesand apply them to three action datasets.We evaluated several video-text models on thetask of retrieval of motion descriptions. Wefound that they fall far behind human expertperformance on two action datasets, raisingthe question of whether video-text models understandmotion in videos. To address it, weintroduce a method of improving motion understandingin video-text models by utilizingmotion descriptions. This method proves tobe effective on two action datasets for the motiondescription retrieval task. The results drawattention to the need for quality captions involvingfine-grained motion information in existingdatasets and demonstrate the effectiveness ofthe proposed pipeline in understanding finegrainedmotion during video-text retrieval.
%U https://aclanthology.org/2024.findings-acl.747
%P 12575-12584
Markdown (Informal)
[Diving Deep into the Motion Representation of Video-Text Models](https://aclanthology.org/2024.findings-acl.747) (Devaraj et al., Findings 2024)
ACL