@inproceedings{ilaslan-etal-2023-gazevqa,
title = "{G}aze{VQA}: A Video Question Answering Dataset for Multiview Eye-Gaze Task-Oriented Collaborations",
author = "Ilaslan, Muhammet and
Song, Chenan and
Chen, Joya and
Gao, Difei and
Lei, Weixian and
Xu, Qianli and
Lim, Joo and
Shou, Mike",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.648",
doi = "10.18653/v1/2023.emnlp-main.648",
pages = "10462--10479",
abstract = "The usage of exocentric and egocentric videos in Video Question Answering (VQA) is a new endeavor in human-robot interaction and collaboration studies. Particularly for egocentric videos, one may leverage eye-gaze information to understand human intentions during the task. In this paper, we build a novel task-oriented VQA dataset, called GazeVQA, for collaborative tasks where gaze information is captured during the task process. GazeVQA is designed with a novel QA format that covers thirteen different reasoning types to capture multiple aspects of task information and user intent. For each participant, GazeVQA consists of more than 1,100 textual questions and more than 500 labeled images that were annotated with the assistance of the Segment Anything Model. In total, 2,967 video clips, 12,491 labeled images, and 25,040 questions from 22 participants were included in the dataset. Additionally, inspired by the assisting models and common ground theory for industrial task collaboration, we propose a new AI model called AssistGaze that is designed to answer the questions with three different answer types, namely textual, image, and video. AssistGaze can effectively ground the perceptual input into semantic information while reducing ambiguities. We conduct comprehensive experiments to demonstrate the challenges of GazeVQA and the effectiveness of AssistGaze.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ilaslan-etal-2023-gazevqa">
<titleInfo>
<title>GazeVQA: A Video Question Answering Dataset for Multiview Eye-Gaze Task-Oriented Collaborations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammet</namePart>
<namePart type="family">Ilaslan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenan</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joya</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Difei</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weixian</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianli</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joo</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Shou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The usage of exocentric and egocentric videos in Video Question Answering (VQA) is a new endeavor in human-robot interaction and collaboration studies. Particularly for egocentric videos, one may leverage eye-gaze information to understand human intentions during the task. In this paper, we build a novel task-oriented VQA dataset, called GazeVQA, for collaborative tasks where gaze information is captured during the task process. GazeVQA is designed with a novel QA format that covers thirteen different reasoning types to capture multiple aspects of task information and user intent. For each participant, GazeVQA consists of more than 1,100 textual questions and more than 500 labeled images that were annotated with the assistance of the Segment Anything Model. In total, 2,967 video clips, 12,491 labeled images, and 25,040 questions from 22 participants were included in the dataset. Additionally, inspired by the assisting models and common ground theory for industrial task collaboration, we propose a new AI model called AssistGaze that is designed to answer the questions with three different answer types, namely textual, image, and video. AssistGaze can effectively ground the perceptual input into semantic information while reducing ambiguities. We conduct comprehensive experiments to demonstrate the challenges of GazeVQA and the effectiveness of AssistGaze.</abstract>
<identifier type="citekey">ilaslan-etal-2023-gazevqa</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.648</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.648</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>10462</start>
<end>10479</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GazeVQA: A Video Question Answering Dataset for Multiview Eye-Gaze Task-Oriented Collaborations
%A Ilaslan, Muhammet
%A Song, Chenan
%A Chen, Joya
%A Gao, Difei
%A Lei, Weixian
%A Xu, Qianli
%A Lim, Joo
%A Shou, Mike
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F ilaslan-etal-2023-gazevqa
%X The usage of exocentric and egocentric videos in Video Question Answering (VQA) is a new endeavor in human-robot interaction and collaboration studies. Particularly for egocentric videos, one may leverage eye-gaze information to understand human intentions during the task. In this paper, we build a novel task-oriented VQA dataset, called GazeVQA, for collaborative tasks where gaze information is captured during the task process. GazeVQA is designed with a novel QA format that covers thirteen different reasoning types to capture multiple aspects of task information and user intent. For each participant, GazeVQA consists of more than 1,100 textual questions and more than 500 labeled images that were annotated with the assistance of the Segment Anything Model. In total, 2,967 video clips, 12,491 labeled images, and 25,040 questions from 22 participants were included in the dataset. Additionally, inspired by the assisting models and common ground theory for industrial task collaboration, we propose a new AI model called AssistGaze that is designed to answer the questions with three different answer types, namely textual, image, and video. AssistGaze can effectively ground the perceptual input into semantic information while reducing ambiguities. We conduct comprehensive experiments to demonstrate the challenges of GazeVQA and the effectiveness of AssistGaze.
%R 10.18653/v1/2023.emnlp-main.648
%U https://aclanthology.org/2023.emnlp-main.648
%U https://doi.org/10.18653/v1/2023.emnlp-main.648
%P 10462-10479
Markdown (Informal)
[GazeVQA: A Video Question Answering Dataset for Multiview Eye-Gaze Task-Oriented Collaborations](https://aclanthology.org/2023.emnlp-main.648) (Ilaslan et al., EMNLP 2023)
ACL