@inproceedings{castro-etal-2020-lifeqa,
title = "{L}ife{QA}: A Real-life Dataset for Video Question Answering",
author = "Castro, Santiago and
Azab, Mahmoud and
Stroud, Jonathan and
Noujaim, Cristina and
Wang, Ruoyao and
Deng, Jia and
Mihalcea, Rada",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.536",
pages = "4352--4358",
abstract = "We introduce LifeQA, a benchmark dataset for video question answering that focuses on day-to-day real-life situations. Current video question answering datasets consist of movies and TV shows. However, it is well-known that these visual domains are not representative of our day-to-day lives. Movies and TV shows, for example, benefit from professional camera movements, clean editing, crisp audio recordings, and scripted dialog between professional actors. While these domains provide a large amount of data for training models, their properties make them unsuitable for testing real-life question answering systems. Our dataset, by contrast, consists of video clips that represent only real-life scenarios. We collect 275 such video clips and over 2.3k multiple-choice questions. In this paper, we analyze the challenging but realistic aspects of LifeQA, and we apply several state-of-the-art video question answering models to provide benchmarks for future research. The full dataset is publicly available at https://lit.eecs.umich.edu/lifeqa/.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="castro-etal-2020-lifeqa">
<titleInfo>
<title>LifeQA: A Real-life Dataset for Video Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Castro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Azab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Stroud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Noujaim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruoyao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jia</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We introduce LifeQA, a benchmark dataset for video question answering that focuses on day-to-day real-life situations. Current video question answering datasets consist of movies and TV shows. However, it is well-known that these visual domains are not representative of our day-to-day lives. Movies and TV shows, for example, benefit from professional camera movements, clean editing, crisp audio recordings, and scripted dialog between professional actors. While these domains provide a large amount of data for training models, their properties make them unsuitable for testing real-life question answering systems. Our dataset, by contrast, consists of video clips that represent only real-life scenarios. We collect 275 such video clips and over 2.3k multiple-choice questions. In this paper, we analyze the challenging but realistic aspects of LifeQA, and we apply several state-of-the-art video question answering models to provide benchmarks for future research. The full dataset is publicly available at https://lit.eecs.umich.edu/lifeqa/.</abstract>
<identifier type="citekey">castro-etal-2020-lifeqa</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.536</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>4352</start>
<end>4358</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LifeQA: A Real-life Dataset for Video Question Answering
%A Castro, Santiago
%A Azab, Mahmoud
%A Stroud, Jonathan
%A Noujaim, Cristina
%A Wang, Ruoyao
%A Deng, Jia
%A Mihalcea, Rada
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F castro-etal-2020-lifeqa
%X We introduce LifeQA, a benchmark dataset for video question answering that focuses on day-to-day real-life situations. Current video question answering datasets consist of movies and TV shows. However, it is well-known that these visual domains are not representative of our day-to-day lives. Movies and TV shows, for example, benefit from professional camera movements, clean editing, crisp audio recordings, and scripted dialog between professional actors. While these domains provide a large amount of data for training models, their properties make them unsuitable for testing real-life question answering systems. Our dataset, by contrast, consists of video clips that represent only real-life scenarios. We collect 275 such video clips and over 2.3k multiple-choice questions. In this paper, we analyze the challenging but realistic aspects of LifeQA, and we apply several state-of-the-art video question answering models to provide benchmarks for future research. The full dataset is publicly available at https://lit.eecs.umich.edu/lifeqa/.
%U https://aclanthology.org/2020.lrec-1.536
%P 4352-4358
Markdown (Informal)
[LifeQA: A Real-life Dataset for Video Question Answering](https://aclanthology.org/2020.lrec-1.536) (Castro et al., LREC 2020)
ACL
- Santiago Castro, Mahmoud Azab, Jonathan Stroud, Cristina Noujaim, Ruoyao Wang, Jia Deng, and Rada Mihalcea. 2020. LifeQA: A Real-life Dataset for Video Question Answering. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 4352–4358, Marseille, France. European Language Resources Association.