@inproceedings{ding-etal-2025-generating,
title = "Generating Questions, Answers, and Distractors for Videos: Exploring Semantic Uncertainty of Object Motions",
author = "Ding, Wenjian and
Zhang, Yao and
Wang, Jun and
Jatowt, Adam and
Yang, Zhenglu",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.376/",
doi = "10.18653/v1/2025.findings-acl.376",
pages = "7207--7220",
ISBN = "979-8-89176-256-5",
abstract = "Video Question-Answer-Distractors (QADs) show promising values for assessing the performance of systems in perceiving and comprehending multimedia content. Given the significant cost and labor demands of manual annotation, existing large-scale Video QADs benchmarks are typically generated automatically using video captions. Since video captions are incomplete representations of visual content and susceptible to error propagation, direct generation of QADs from video is crucial. This work first leverages a large vision-language model for video QADs generation. To enhance the consistency and diversity of the generated QADs, we propose utilizing temporal motion to describe the video objects. In addition, We design a selection mechanism that chooses diverse temporal object motions to generate diverse QADs focusing on different objects and interactions, maximizing overall semantic uncertainty for a given video. Evaluation on the NExT-QA and Perception Test benchmarks demonstrates that the proposed approach significantly improves both the consistency and diversity of QADs generated by a range of large vision-language models, thus highlighting its effectiveness and generalizability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2025-generating">
<titleInfo>
<title>Generating Questions, Answers, and Distractors for Videos: Exploring Semantic Uncertainty of Object Motions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenjian</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Jatowt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenglu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Video Question-Answer-Distractors (QADs) show promising values for assessing the performance of systems in perceiving and comprehending multimedia content. Given the significant cost and labor demands of manual annotation, existing large-scale Video QADs benchmarks are typically generated automatically using video captions. Since video captions are incomplete representations of visual content and susceptible to error propagation, direct generation of QADs from video is crucial. This work first leverages a large vision-language model for video QADs generation. To enhance the consistency and diversity of the generated QADs, we propose utilizing temporal motion to describe the video objects. In addition, We design a selection mechanism that chooses diverse temporal object motions to generate diverse QADs focusing on different objects and interactions, maximizing overall semantic uncertainty for a given video. Evaluation on the NExT-QA and Perception Test benchmarks demonstrates that the proposed approach significantly improves both the consistency and diversity of QADs generated by a range of large vision-language models, thus highlighting its effectiveness and generalizability.</abstract>
<identifier type="citekey">ding-etal-2025-generating</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.376</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.376/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>7207</start>
<end>7220</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Questions, Answers, and Distractors for Videos: Exploring Semantic Uncertainty of Object Motions
%A Ding, Wenjian
%A Zhang, Yao
%A Wang, Jun
%A Jatowt, Adam
%A Yang, Zhenglu
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F ding-etal-2025-generating
%X Video Question-Answer-Distractors (QADs) show promising values for assessing the performance of systems in perceiving and comprehending multimedia content. Given the significant cost and labor demands of manual annotation, existing large-scale Video QADs benchmarks are typically generated automatically using video captions. Since video captions are incomplete representations of visual content and susceptible to error propagation, direct generation of QADs from video is crucial. This work first leverages a large vision-language model for video QADs generation. To enhance the consistency and diversity of the generated QADs, we propose utilizing temporal motion to describe the video objects. In addition, We design a selection mechanism that chooses diverse temporal object motions to generate diverse QADs focusing on different objects and interactions, maximizing overall semantic uncertainty for a given video. Evaluation on the NExT-QA and Perception Test benchmarks demonstrates that the proposed approach significantly improves both the consistency and diversity of QADs generated by a range of large vision-language models, thus highlighting its effectiveness and generalizability.
%R 10.18653/v1/2025.findings-acl.376
%U https://aclanthology.org/2025.findings-acl.376/
%U https://doi.org/10.18653/v1/2025.findings-acl.376
%P 7207-7220
Markdown (Informal)
[Generating Questions, Answers, and Distractors for Videos: Exploring Semantic Uncertainty of Object Motions](https://aclanthology.org/2025.findings-acl.376/) (Ding et al., Findings 2025)
ACL