@inproceedings{nishimura-etal-2024-text360nav,
title = "{T}ext360{N}av: 360-Degree Image Captioning Dataset for Urban Pedestrians Navigation",
author = "Nishimura, Chieko and
Kurita, Shuhei and
Seki, Yohei",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1371",
pages = "15783--15788",
abstract = "Text feedback from urban scenes is a crucial tool for pedestrians to understand surroundings, obstacles, and safe pathways. However, existing image captioning datasets often concentrate on the overall image description and lack detailed scene descriptions, overlooking features for pedestrians walking on urban streets. We developed a new dataset to assist pedestrians in urban scenes using 360-degree camera images. Through our dataset of Text360Nav, we aim to provide textual feedback from machinery visual perception such as 360-degree cameras to visually impaired individuals and distracted pedestrians navigating urban streets, including those engrossed in their smartphones while walking. In experiments, we combined our dataset with multimodal generative models and observed that models trained with our dataset can generate textual descriptions focusing on street objects and obstacles that are meaningful in urban scenes in both quantitative and qualitative analyses, thus supporting the effectiveness of our dataset for urban pedestrian navigation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishimura-etal-2024-text360nav">
<titleInfo>
<title>Text360Nav: 360-Degree Image Captioning Dataset for Urban Pedestrians Navigation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chieko</namePart>
<namePart type="family">Nishimura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuhei</namePart>
<namePart type="family">Kurita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yohei</namePart>
<namePart type="family">Seki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</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">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text feedback from urban scenes is a crucial tool for pedestrians to understand surroundings, obstacles, and safe pathways. However, existing image captioning datasets often concentrate on the overall image description and lack detailed scene descriptions, overlooking features for pedestrians walking on urban streets. We developed a new dataset to assist pedestrians in urban scenes using 360-degree camera images. Through our dataset of Text360Nav, we aim to provide textual feedback from machinery visual perception such as 360-degree cameras to visually impaired individuals and distracted pedestrians navigating urban streets, including those engrossed in their smartphones while walking. In experiments, we combined our dataset with multimodal generative models and observed that models trained with our dataset can generate textual descriptions focusing on street objects and obstacles that are meaningful in urban scenes in both quantitative and qualitative analyses, thus supporting the effectiveness of our dataset for urban pedestrian navigation.</abstract>
<identifier type="citekey">nishimura-etal-2024-text360nav</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1371</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15783</start>
<end>15788</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text360Nav: 360-Degree Image Captioning Dataset for Urban Pedestrians Navigation
%A Nishimura, Chieko
%A Kurita, Shuhei
%A Seki, Yohei
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F nishimura-etal-2024-text360nav
%X Text feedback from urban scenes is a crucial tool for pedestrians to understand surroundings, obstacles, and safe pathways. However, existing image captioning datasets often concentrate on the overall image description and lack detailed scene descriptions, overlooking features for pedestrians walking on urban streets. We developed a new dataset to assist pedestrians in urban scenes using 360-degree camera images. Through our dataset of Text360Nav, we aim to provide textual feedback from machinery visual perception such as 360-degree cameras to visually impaired individuals and distracted pedestrians navigating urban streets, including those engrossed in their smartphones while walking. In experiments, we combined our dataset with multimodal generative models and observed that models trained with our dataset can generate textual descriptions focusing on street objects and obstacles that are meaningful in urban scenes in both quantitative and qualitative analyses, thus supporting the effectiveness of our dataset for urban pedestrian navigation.
%U https://aclanthology.org/2024.lrec-main.1371
%P 15783-15788
Markdown (Informal)
[Text360Nav: 360-Degree Image Captioning Dataset for Urban Pedestrians Navigation](https://aclanthology.org/2024.lrec-main.1371) (Nishimura et al., LREC-COLING 2024)
ACL