@inproceedings{kido-shimomoto-etal-2023-towards,
title = "Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding",
author = "Kido Shimomoto, Erica and
Marrese-Taylor, Edison and
Takamura, Hiroya and
Kobayashi, Ichiro and
Nakayama, Hideki and
Miyao, Yusuke",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.829",
doi = "10.18653/v1/2023.findings-acl.829",
pages = "13101--13123",
abstract = "This paper explores the task of Temporal Video Grounding (TVG) where, given an untrimmed video and a query sentence, the goal is to recognize and determine temporal boundaries of action instances in the video described by natural language queries. Recent works tackled this task by improving query inputs with large pre-trained language models (PLM), at the cost of more expensive training. However, the effects of this integration are unclear, as these works also propose improvements in the visual inputs. Therefore, this paper studies the role of query sentence representation with PLMs in TVG and assesses the applicability of parameter-efficient training with NLP adapters. We couple popular PLMs with a selection of existing approaches and test different adapters to reduce the impact of the additional parameters. Our results on three challenging datasets show that, with the same visual inputs, TVG models greatly benefited from the PLM integration and fine-tuning, stressing the importance of the text query representation in this task. Furthermore, adapters were an effective alternative to full fine-tuning, even though they are not tailored to our task, allowing PLM integration in larger TVG models and delivering results comparable to SOTA models. Finally, our results shed light on which adapters work best in different scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kido-shimomoto-etal-2023-towards">
<titleInfo>
<title>Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erica</namePart>
<namePart type="family">Kido Shimomoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edison</namePart>
<namePart type="family">Marrese-Taylor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ichiro</namePart>
<namePart type="family">Kobayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Nakayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper explores the task of Temporal Video Grounding (TVG) where, given an untrimmed video and a query sentence, the goal is to recognize and determine temporal boundaries of action instances in the video described by natural language queries. Recent works tackled this task by improving query inputs with large pre-trained language models (PLM), at the cost of more expensive training. However, the effects of this integration are unclear, as these works also propose improvements in the visual inputs. Therefore, this paper studies the role of query sentence representation with PLMs in TVG and assesses the applicability of parameter-efficient training with NLP adapters. We couple popular PLMs with a selection of existing approaches and test different adapters to reduce the impact of the additional parameters. Our results on three challenging datasets show that, with the same visual inputs, TVG models greatly benefited from the PLM integration and fine-tuning, stressing the importance of the text query representation in this task. Furthermore, adapters were an effective alternative to full fine-tuning, even though they are not tailored to our task, allowing PLM integration in larger TVG models and delivering results comparable to SOTA models. Finally, our results shed light on which adapters work best in different scenarios.</abstract>
<identifier type="citekey">kido-shimomoto-etal-2023-towards</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.829</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.829</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>13101</start>
<end>13123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding
%A Kido Shimomoto, Erica
%A Marrese-Taylor, Edison
%A Takamura, Hiroya
%A Kobayashi, Ichiro
%A Nakayama, Hideki
%A Miyao, Yusuke
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F kido-shimomoto-etal-2023-towards
%X This paper explores the task of Temporal Video Grounding (TVG) where, given an untrimmed video and a query sentence, the goal is to recognize and determine temporal boundaries of action instances in the video described by natural language queries. Recent works tackled this task by improving query inputs with large pre-trained language models (PLM), at the cost of more expensive training. However, the effects of this integration are unclear, as these works also propose improvements in the visual inputs. Therefore, this paper studies the role of query sentence representation with PLMs in TVG and assesses the applicability of parameter-efficient training with NLP adapters. We couple popular PLMs with a selection of existing approaches and test different adapters to reduce the impact of the additional parameters. Our results on three challenging datasets show that, with the same visual inputs, TVG models greatly benefited from the PLM integration and fine-tuning, stressing the importance of the text query representation in this task. Furthermore, adapters were an effective alternative to full fine-tuning, even though they are not tailored to our task, allowing PLM integration in larger TVG models and delivering results comparable to SOTA models. Finally, our results shed light on which adapters work best in different scenarios.
%R 10.18653/v1/2023.findings-acl.829
%U https://aclanthology.org/2023.findings-acl.829
%U https://doi.org/10.18653/v1/2023.findings-acl.829
%P 13101-13123
Markdown (Informal)
[Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding](https://aclanthology.org/2023.findings-acl.829) (Kido Shimomoto et al., Findings 2023)
ACL