@inproceedings{ignat-etal-2021-whyact,
title = "{W}hy{A}ct: Identifying Action Reasons in Lifestyle Vlogs",
author = "Ignat, Oana and
Castro, Santiago and
Miao, Hanwen and
Li, Weiji and
Mihalcea, Rada",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.392/",
doi = "10.18653/v1/2021.emnlp-main.392",
pages = "4770--4785",
abstract = "We aim to automatically identify human action reasons in online videos. We focus on the widespread genre of lifestyle vlogs, in which people perform actions while verbally describing them. We introduce and make publicly available the WhyAct dataset, consisting of 1,077 visual actions manually annotated with their reasons. We describe a multimodal model that leverages visual and textual information to automatically infer the reasons corresponding to an action presented in the video."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ignat-etal-2021-whyact">
<titleInfo>
<title>WhyAct: Identifying Action Reasons in Lifestyle Vlogs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Ignat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Hanwen</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiji</namePart>
<namePart type="family">Li</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>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We aim to automatically identify human action reasons in online videos. We focus on the widespread genre of lifestyle vlogs, in which people perform actions while verbally describing them. We introduce and make publicly available the WhyAct dataset, consisting of 1,077 visual actions manually annotated with their reasons. We describe a multimodal model that leverages visual and textual information to automatically infer the reasons corresponding to an action presented in the video.</abstract>
<identifier type="citekey">ignat-etal-2021-whyact</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.392</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.392/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4770</start>
<end>4785</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WhyAct: Identifying Action Reasons in Lifestyle Vlogs
%A Ignat, Oana
%A Castro, Santiago
%A Miao, Hanwen
%A Li, Weiji
%A Mihalcea, Rada
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F ignat-etal-2021-whyact
%X We aim to automatically identify human action reasons in online videos. We focus on the widespread genre of lifestyle vlogs, in which people perform actions while verbally describing them. We introduce and make publicly available the WhyAct dataset, consisting of 1,077 visual actions manually annotated with their reasons. We describe a multimodal model that leverages visual and textual information to automatically infer the reasons corresponding to an action presented in the video.
%R 10.18653/v1/2021.emnlp-main.392
%U https://aclanthology.org/2021.emnlp-main.392/
%U https://doi.org/10.18653/v1/2021.emnlp-main.392
%P 4770-4785
Markdown (Informal)
[WhyAct: Identifying Action Reasons in Lifestyle Vlogs](https://aclanthology.org/2021.emnlp-main.392/) (Ignat et al., EMNLP 2021)
ACL
- Oana Ignat, Santiago Castro, Hanwen Miao, Weiji Li, and Rada Mihalcea. 2021. WhyAct: Identifying Action Reasons in Lifestyle Vlogs. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4770–4785, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.