@inproceedings{park-etal-2022-exposing,
title = "Exposing the Limits of Video-Text Models through Contrast Sets",
author = "Park, Jae Sung and
Shen, Sheng and
Farhadi, Ali and
Darrell, Trevor and
Choi, Yejin and
Rohrbach, Anna",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.261",
doi = "10.18653/v1/2022.naacl-main.261",
pages = "3574--3586",
abstract = "Recent video-text models can retrieve relevant videos based on text with a high accuracy, but to what extent do they comprehend the semantics of the text? Can they discriminate between similar entities and actions? To answer this, we propose an evaluation framework that probes video-text models with hard negatives. We automatically build contrast sets, where true textual descriptions are manipulated in ways that change their semantics while maintaining plausibility. Specifically, we leverage a pre-trained language model and a set of heuristics to create verb and person entity focused contrast sets. We apply these in the multiple choice video to-text classification setting. We test the robustness of recent methods on the proposed automatic contrast sets, and compare them to additionally collected human-generated counterparts, to assess their effectiveness. We see that model performance suffers across all methods, erasing the gap between recent CLIP-based methods vs. the earlier methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2022-exposing">
<titleInfo>
<title>Exposing the Limits of Video-Text Models through Contrast Sets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jae</namePart>
<namePart type="given">Sung</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Farhadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Darrell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yejin</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rohrbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent video-text models can retrieve relevant videos based on text with a high accuracy, but to what extent do they comprehend the semantics of the text? Can they discriminate between similar entities and actions? To answer this, we propose an evaluation framework that probes video-text models with hard negatives. We automatically build contrast sets, where true textual descriptions are manipulated in ways that change their semantics while maintaining plausibility. Specifically, we leverage a pre-trained language model and a set of heuristics to create verb and person entity focused contrast sets. We apply these in the multiple choice video to-text classification setting. We test the robustness of recent methods on the proposed automatic contrast sets, and compare them to additionally collected human-generated counterparts, to assess their effectiveness. We see that model performance suffers across all methods, erasing the gap between recent CLIP-based methods vs. the earlier methods.</abstract>
<identifier type="citekey">park-etal-2022-exposing</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.261</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.261</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>3574</start>
<end>3586</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exposing the Limits of Video-Text Models through Contrast Sets
%A Park, Jae Sung
%A Shen, Sheng
%A Farhadi, Ali
%A Darrell, Trevor
%A Choi, Yejin
%A Rohrbach, Anna
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F park-etal-2022-exposing
%X Recent video-text models can retrieve relevant videos based on text with a high accuracy, but to what extent do they comprehend the semantics of the text? Can they discriminate between similar entities and actions? To answer this, we propose an evaluation framework that probes video-text models with hard negatives. We automatically build contrast sets, where true textual descriptions are manipulated in ways that change their semantics while maintaining plausibility. Specifically, we leverage a pre-trained language model and a set of heuristics to create verb and person entity focused contrast sets. We apply these in the multiple choice video to-text classification setting. We test the robustness of recent methods on the proposed automatic contrast sets, and compare them to additionally collected human-generated counterparts, to assess their effectiveness. We see that model performance suffers across all methods, erasing the gap between recent CLIP-based methods vs. the earlier methods.
%R 10.18653/v1/2022.naacl-main.261
%U https://aclanthology.org/2022.naacl-main.261
%U https://doi.org/10.18653/v1/2022.naacl-main.261
%P 3574-3586
Markdown (Informal)
[Exposing the Limits of Video-Text Models through Contrast Sets](https://aclanthology.org/2022.naacl-main.261) (Park et al., NAACL 2022)
ACL
- Jae Sung Park, Sheng Shen, Ali Farhadi, Trevor Darrell, Yejin Choi, and Anna Rohrbach. 2022. Exposing the Limits of Video-Text Models through Contrast Sets. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3574–3586, Seattle, United States. Association for Computational Linguistics.