@inproceedings{kamezawa-etal-2020-visually,
title = "A Visually-grounded First-person Dialogue Dataset with Verbal and Non-verbal Responses",
author = "Kamezawa, Hisashi and
Nishida, Noriki and
Shimizu, Nobuyuki and
Miyazaki, Takashi and
Nakayama, Hideki",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.267",
doi = "10.18653/v1/2020.emnlp-main.267",
pages = "3299--3310",
abstract = "In real-world dialogue, first-person visual information about where the other speakers are and what they are paying attention to is crucial to understand their intentions. Non-verbal responses also play an important role in social interactions. In this paper, we propose a visually-grounded first-person dialogue (VFD) dataset with verbal and non-verbal responses. The VFD dataset provides manually annotated (1) first-person images of agents, (2) utterances of human speakers, (3) eye-gaze locations of the speakers, and (4) the agents{'} verbal and non-verbal responses. We present experimental results obtained using the proposed VFD dataset and recent neural network models (e.g., BERT, ResNet). The results demonstrate that first-person vision helps neural network models correctly understand human intentions, and the production of non-verbal responses is a challenging task like that of verbal responses. Our dataset is publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kamezawa-etal-2020-visually">
<titleInfo>
<title>A Visually-grounded First-person Dialogue Dataset with Verbal and Non-verbal Responses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hisashi</namePart>
<namePart type="family">Kamezawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noriki</namePart>
<namePart type="family">Nishida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nobuyuki</namePart>
<namePart type="family">Shimizu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Miyazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Nakayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In real-world dialogue, first-person visual information about where the other speakers are and what they are paying attention to is crucial to understand their intentions. Non-verbal responses also play an important role in social interactions. In this paper, we propose a visually-grounded first-person dialogue (VFD) dataset with verbal and non-verbal responses. The VFD dataset provides manually annotated (1) first-person images of agents, (2) utterances of human speakers, (3) eye-gaze locations of the speakers, and (4) the agents’ verbal and non-verbal responses. We present experimental results obtained using the proposed VFD dataset and recent neural network models (e.g., BERT, ResNet). The results demonstrate that first-person vision helps neural network models correctly understand human intentions, and the production of non-verbal responses is a challenging task like that of verbal responses. Our dataset is publicly available.</abstract>
<identifier type="citekey">kamezawa-etal-2020-visually</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.267</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.267</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3299</start>
<end>3310</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Visually-grounded First-person Dialogue Dataset with Verbal and Non-verbal Responses
%A Kamezawa, Hisashi
%A Nishida, Noriki
%A Shimizu, Nobuyuki
%A Miyazaki, Takashi
%A Nakayama, Hideki
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F kamezawa-etal-2020-visually
%X In real-world dialogue, first-person visual information about where the other speakers are and what they are paying attention to is crucial to understand their intentions. Non-verbal responses also play an important role in social interactions. In this paper, we propose a visually-grounded first-person dialogue (VFD) dataset with verbal and non-verbal responses. The VFD dataset provides manually annotated (1) first-person images of agents, (2) utterances of human speakers, (3) eye-gaze locations of the speakers, and (4) the agents’ verbal and non-verbal responses. We present experimental results obtained using the proposed VFD dataset and recent neural network models (e.g., BERT, ResNet). The results demonstrate that first-person vision helps neural network models correctly understand human intentions, and the production of non-verbal responses is a challenging task like that of verbal responses. Our dataset is publicly available.
%R 10.18653/v1/2020.emnlp-main.267
%U https://aclanthology.org/2020.emnlp-main.267
%U https://doi.org/10.18653/v1/2020.emnlp-main.267
%P 3299-3310
Markdown (Informal)
[A Visually-grounded First-person Dialogue Dataset with Verbal and Non-verbal Responses](https://aclanthology.org/2020.emnlp-main.267) (Kamezawa et al., EMNLP 2020)
ACL