@inproceedings{kronberger-ventura-2024-thavqa,
title = "{THAVQA}: A {G}erman Task-oriented {VQA} Dataset Annotated with Human Visual Attention",
author = "Kronberger, Moritz and
Ventura, Viviana",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.55/",
pages = "459--469",
ISBN = "979-12-210-7060-6",
abstract = "Video question answering (VQA) is a challenging task that requires models to generate answers by using both information from text and video. We present Task-oriented Human Attention Video Question Answering (THAVQA), a new VQA dataset consisting of third- and first- person videos of an instructor using a sewing machine. The sewing task is formalized step-by-step in a script: each step consists of a video annotated with German language open-ended question and answer (QA) pairs and with human visual attention. The paper also includes a first assessment of the performance of a pre-trained Multimodal Large Language Model (MLLM) in generating answers to the questions of our dataset across different experimental settings.Results show that our task-oriented dataset is challenging for pre-trained models. Specifically, the model struggles to answer questions requiring technical knowledge or spatio-temporal reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kronberger-ventura-2024-thavqa">
<titleInfo>
<title>THAVQA: A German Task-oriented VQA Dataset Annotated with Human Visual Attention</title>
</titleInfo>
<name type="personal">
<namePart type="given">Moritz</namePart>
<namePart type="family">Kronberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviana</namePart>
<namePart type="family">Ventura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>Video question answering (VQA) is a challenging task that requires models to generate answers by using both information from text and video. We present Task-oriented Human Attention Video Question Answering (THAVQA), a new VQA dataset consisting of third- and first- person videos of an instructor using a sewing machine. The sewing task is formalized step-by-step in a script: each step consists of a video annotated with German language open-ended question and answer (QA) pairs and with human visual attention. The paper also includes a first assessment of the performance of a pre-trained Multimodal Large Language Model (MLLM) in generating answers to the questions of our dataset across different experimental settings.Results show that our task-oriented dataset is challenging for pre-trained models. Specifically, the model struggles to answer questions requiring technical knowledge or spatio-temporal reasoning.</abstract>
<identifier type="citekey">kronberger-ventura-2024-thavqa</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.55/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>459</start>
<end>469</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T THAVQA: A German Task-oriented VQA Dataset Annotated with Human Visual Attention
%A Kronberger, Moritz
%A Ventura, Viviana
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F kronberger-ventura-2024-thavqa
%X Video question answering (VQA) is a challenging task that requires models to generate answers by using both information from text and video. We present Task-oriented Human Attention Video Question Answering (THAVQA), a new VQA dataset consisting of third- and first- person videos of an instructor using a sewing machine. The sewing task is formalized step-by-step in a script: each step consists of a video annotated with German language open-ended question and answer (QA) pairs and with human visual attention. The paper also includes a first assessment of the performance of a pre-trained Multimodal Large Language Model (MLLM) in generating answers to the questions of our dataset across different experimental settings.Results show that our task-oriented dataset is challenging for pre-trained models. Specifically, the model struggles to answer questions requiring technical knowledge or spatio-temporal reasoning.
%U https://aclanthology.org/2024.clicit-1.55/
%P 459-469
Markdown (Informal)
[THAVQA: A German Task-oriented VQA Dataset Annotated with Human Visual Attention](https://aclanthology.org/2024.clicit-1.55/) (Kronberger & Ventura, CLiC-it 2024)
ACL