@inproceedings{zheng-etal-2023-generating,
title = "Generating Structured Pseudo Labels for Noise-resistant Zero-shot Video Sentence Localization",
author = "Zheng, Minghang and
Gong, Shaogang and
Jin, Hailin and
Peng, Yuxin and
Liu, Yang",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.794",
doi = "10.18653/v1/2023.acl-long.794",
pages = "14197--14209",
abstract = "Video sentence localization aims to locate moments in an unstructured video according to a given natural language query. A main challenge is the expensive annotation costs and the annotation bias. In this work, we study video sentence localization in a zero-shot setting, which learns with only video data without any annotation. Existing zero-shot pipelines usually generate event proposals and then generate a pseudo query for each event proposal. However, their event proposals are obtained via visual feature clustering, which is query-independent and inaccurate; and the pseudo-queries are short or less interpretable. Moreover, existing approaches ignores the risk of pseudo-label noise when leveraging them in training. To address the above problems, we propose a Structure-based Pseudo Label generation (SPL), which first generate free-form interpretable pseudo queries before constructing query-dependent event proposals by modeling the event temporal structure. To mitigate the effect of pseudo-label noise, we propose a noise-resistant iterative method that repeatedly re-weight the training sample based on noise estimation to train a grounding model and correct pseudo labels. Experiments on the ActivityNet Captions and Charades-STA datasets demonstrate the advantages of our approach. Code can be found at \url{https://github.com/minghangz/SPL}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2023-generating">
<titleInfo>
<title>Generating Structured Pseudo Labels for Noise-resistant Zero-shot Video Sentence Localization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minghang</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaogang</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hailin</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxin</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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>Video sentence localization aims to locate moments in an unstructured video according to a given natural language query. A main challenge is the expensive annotation costs and the annotation bias. In this work, we study video sentence localization in a zero-shot setting, which learns with only video data without any annotation. Existing zero-shot pipelines usually generate event proposals and then generate a pseudo query for each event proposal. However, their event proposals are obtained via visual feature clustering, which is query-independent and inaccurate; and the pseudo-queries are short or less interpretable. Moreover, existing approaches ignores the risk of pseudo-label noise when leveraging them in training. To address the above problems, we propose a Structure-based Pseudo Label generation (SPL), which first generate free-form interpretable pseudo queries before constructing query-dependent event proposals by modeling the event temporal structure. To mitigate the effect of pseudo-label noise, we propose a noise-resistant iterative method that repeatedly re-weight the training sample based on noise estimation to train a grounding model and correct pseudo labels. Experiments on the ActivityNet Captions and Charades-STA datasets demonstrate the advantages of our approach. Code can be found at https://github.com/minghangz/SPL.</abstract>
<identifier type="citekey">zheng-etal-2023-generating</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.794</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.794</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>14197</start>
<end>14209</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Structured Pseudo Labels for Noise-resistant Zero-shot Video Sentence Localization
%A Zheng, Minghang
%A Gong, Shaogang
%A Jin, Hailin
%A Peng, Yuxin
%A Liu, Yang
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zheng-etal-2023-generating
%X Video sentence localization aims to locate moments in an unstructured video according to a given natural language query. A main challenge is the expensive annotation costs and the annotation bias. In this work, we study video sentence localization in a zero-shot setting, which learns with only video data without any annotation. Existing zero-shot pipelines usually generate event proposals and then generate a pseudo query for each event proposal. However, their event proposals are obtained via visual feature clustering, which is query-independent and inaccurate; and the pseudo-queries are short or less interpretable. Moreover, existing approaches ignores the risk of pseudo-label noise when leveraging them in training. To address the above problems, we propose a Structure-based Pseudo Label generation (SPL), which first generate free-form interpretable pseudo queries before constructing query-dependent event proposals by modeling the event temporal structure. To mitigate the effect of pseudo-label noise, we propose a noise-resistant iterative method that repeatedly re-weight the training sample based on noise estimation to train a grounding model and correct pseudo labels. Experiments on the ActivityNet Captions and Charades-STA datasets demonstrate the advantages of our approach. Code can be found at https://github.com/minghangz/SPL.
%R 10.18653/v1/2023.acl-long.794
%U https://aclanthology.org/2023.acl-long.794
%U https://doi.org/10.18653/v1/2023.acl-long.794
%P 14197-14209
Markdown (Informal)
[Generating Structured Pseudo Labels for Noise-resistant Zero-shot Video Sentence Localization](https://aclanthology.org/2023.acl-long.794) (Zheng et al., ACL 2023)
ACL