No Cover Image

Conference Paper/Proceeding/Abstract 8 views 1 download

The ORBIT India Dataset: Understanding the Challenges of Collecting a Disability-First AI Dataset in Low-Resource Environments

Gesu India, Martin Grayson Orcid Logo, Cecily Morrison Orcid Logo, Daniela Massiceti Orcid Logo, Simon Robinson Orcid Logo, Jen Pearson Orcid Logo, Matt Jones Orcid Logo

Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, Pages: 1 - 15

Swansea University Authors: Gesu India, Simon Robinson Orcid Logo, Jen Pearson Orcid Logo, Matt Jones Orcid Logo

  • 71273.VOR.pdf

    PDF | Version of Record

    © 2026 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution 4.0 International License.

    Download (939.12KB)

DOI (Published version): 10.1145/3772318.3791099

Abstract

Computer vision systems are increasingly used by blind individuals to navigate their lives, helping, for example, locate objects such as doors or chairs. Yet these recognition systems do not work for many personal objects a blind user might want to find, such as keys or a special notebook. In respon...

Full description

Published in: Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems
ISBN: 979-8-4007-2278-3
Published: New York, NY, USA Association for Computing Machinery (ACM) 2026
URI: https://cronfa.swan.ac.uk/Record/cronfa71273
first_indexed 2026-01-19T16:01:39Z
last_indexed 2026-05-15T10:27:57Z
id cronfa71273
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>71273</id><entry>2026-01-19</entry><title>The ORBIT India Dataset: Understanding the Challenges of Collecting a Disability-First AI Dataset in Low-Resource Environments</title><swanseaauthors><author><sid>4c5e1c0d6f918a2374993b2c5a25d20a</sid><ORCID/><firstname>Gesu</firstname><surname>India</surname><name>Gesu India</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>cb3b57a21fa4e48ec633d6ba46455e91</sid><ORCID>0000-0001-9228-006X</ORCID><firstname>Simon</firstname><surname>Robinson</surname><name>Simon Robinson</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>6d662d9e2151b302ed384b243e2a802f</sid><ORCID>0000-0002-1960-1012</ORCID><firstname>Jen</firstname><surname>Pearson</surname><name>Jen Pearson</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>10b46d7843c2ba53d116ca2ed9abb56e</sid><ORCID>0000-0001-7657-7373</ORCID><firstname>Matt</firstname><surname>Jones</surname><name>Matt Jones</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-01-19</date><deptcode>EAAS</deptcode><abstract>Computer vision systems are increasingly used by blind individuals to navigate their lives, helping, for example, locate objects such as doors or chairs. Yet these recognition systems do not work for many personal objects a blind user might want to find, such as keys or a special notebook. In response, efforts created personalized recognition systems, where individuals train their phones to identify and locate things, like a coffee mug or white cane, using example images/videos. However, these tools are trained on data from high-resource contexts, not necessarily reflecting India’s material culture. This paper discusses the contribution of the ORBIT-India dataset, which extends these tools to the Indian context, home of the world’s largest blind population. The ORBIT-India dataset comprises 105,243 images from 587 videos, representing 76 unique objects. We use this experience to examine dataset collection practices translated from high- to low-resource settings, providing recommendations to support cross-geography dataset collection.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems</journal><volume/><journalNumber/><paginationStart>1</paginationStart><paginationEnd>15</paginationEnd><publisher>Association for Computing Machinery (ACM)</publisher><placeOfPublication>New York, NY, USA</placeOfPublication><isbnPrint/><isbnElectronic>979-8-4007-2278-3</isbnElectronic><issnPrint/><issnElectronic/><keywords>AI, accessibility, datasets, teachable object recognition, vision impairment, Global South</keywords><publishedDay>13</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-04-13</publishedDate><doi>10.1145/3772318.3791099</doi><url/><notes/><college>COLLEGE NANME</college><department>Engineering and Applied Sciences School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EAAS</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>This work was supported by Engineering and Physical Sciences Research Council grant EP/Y010477/1 and by an EPSRC–Microsoft Research ICASE Award (EP/W522053/1).</funders><projectreference/><lastEdited>2026-05-15T11:34:41.3933910</lastEdited><Created>2026-01-19T11:02:31.6316347</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Gesu</firstname><surname>India</surname><orcid/><order>1</order></author><author><firstname>Martin</firstname><surname>Grayson</surname><orcid>0000-0002-0895-3098</orcid><order>2</order></author><author><firstname>Cecily</firstname><surname>Morrison</surname><orcid>0000-0001-5013-3715</orcid><order>3</order></author><author><firstname>Daniela</firstname><surname>Massiceti</surname><orcid>0000-0002-1273-0591</orcid><order>4</order></author><author><firstname>Simon</firstname><surname>Robinson</surname><orcid>0000-0001-9228-006X</orcid><order>5</order></author><author><firstname>Jen</firstname><surname>Pearson</surname><orcid>0000-0002-1960-1012</orcid><order>6</order></author><author><firstname>Matt</firstname><surname>Jones</surname><orcid>0000-0001-7657-7373</orcid><order>7</order></author></authors><documents><document><filename>71273__36741__e05277fa0790496bb39f22e97f776c92.pdf</filename><originalFilename>71273.VOR.pdf</originalFilename><uploaded>2026-05-15T11:26:52.5206748</uploaded><type>Output</type><contentLength>961659</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2026 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution 4.0 International License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 71273 2026-01-19 The ORBIT India Dataset: Understanding the Challenges of Collecting a Disability-First AI Dataset in Low-Resource Environments 4c5e1c0d6f918a2374993b2c5a25d20a Gesu India Gesu India true false cb3b57a21fa4e48ec633d6ba46455e91 0000-0001-9228-006X Simon Robinson Simon Robinson true false 6d662d9e2151b302ed384b243e2a802f 0000-0002-1960-1012 Jen Pearson Jen Pearson true false 10b46d7843c2ba53d116ca2ed9abb56e 0000-0001-7657-7373 Matt Jones Matt Jones true false 2026-01-19 EAAS Computer vision systems are increasingly used by blind individuals to navigate their lives, helping, for example, locate objects such as doors or chairs. Yet these recognition systems do not work for many personal objects a blind user might want to find, such as keys or a special notebook. In response, efforts created personalized recognition systems, where individuals train their phones to identify and locate things, like a coffee mug or white cane, using example images/videos. However, these tools are trained on data from high-resource contexts, not necessarily reflecting India’s material culture. This paper discusses the contribution of the ORBIT-India dataset, which extends these tools to the Indian context, home of the world’s largest blind population. The ORBIT-India dataset comprises 105,243 images from 587 videos, representing 76 unique objects. We use this experience to examine dataset collection practices translated from high- to low-resource settings, providing recommendations to support cross-geography dataset collection. Conference Paper/Proceeding/Abstract Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems 1 15 Association for Computing Machinery (ACM) New York, NY, USA 979-8-4007-2278-3 AI, accessibility, datasets, teachable object recognition, vision impairment, Global South 13 4 2026 2026-04-13 10.1145/3772318.3791099 COLLEGE NANME Engineering and Applied Sciences School COLLEGE CODE EAAS Swansea University SU Library paid the OA fee (TA Institutional Deal) This work was supported by Engineering and Physical Sciences Research Council grant EP/Y010477/1 and by an EPSRC–Microsoft Research ICASE Award (EP/W522053/1). 2026-05-15T11:34:41.3933910 2026-01-19T11:02:31.6316347 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Gesu India 1 Martin Grayson 0000-0002-0895-3098 2 Cecily Morrison 0000-0001-5013-3715 3 Daniela Massiceti 0000-0002-1273-0591 4 Simon Robinson 0000-0001-9228-006X 5 Jen Pearson 0000-0002-1960-1012 6 Matt Jones 0000-0001-7657-7373 7 71273__36741__e05277fa0790496bb39f22e97f776c92.pdf 71273.VOR.pdf 2026-05-15T11:26:52.5206748 Output 961659 application/pdf Version of Record true © 2026 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution 4.0 International License. true eng https://creativecommons.org/licenses/by/4.0/
title The ORBIT India Dataset: Understanding the Challenges of Collecting a Disability-First AI Dataset in Low-Resource Environments
spellingShingle The ORBIT India Dataset: Understanding the Challenges of Collecting a Disability-First AI Dataset in Low-Resource Environments
Gesu India
Simon Robinson
Jen Pearson
Matt Jones
title_short The ORBIT India Dataset: Understanding the Challenges of Collecting a Disability-First AI Dataset in Low-Resource Environments
title_full The ORBIT India Dataset: Understanding the Challenges of Collecting a Disability-First AI Dataset in Low-Resource Environments
title_fullStr The ORBIT India Dataset: Understanding the Challenges of Collecting a Disability-First AI Dataset in Low-Resource Environments
title_full_unstemmed The ORBIT India Dataset: Understanding the Challenges of Collecting a Disability-First AI Dataset in Low-Resource Environments
title_sort The ORBIT India Dataset: Understanding the Challenges of Collecting a Disability-First AI Dataset in Low-Resource Environments
author_id_str_mv 4c5e1c0d6f918a2374993b2c5a25d20a
cb3b57a21fa4e48ec633d6ba46455e91
6d662d9e2151b302ed384b243e2a802f
10b46d7843c2ba53d116ca2ed9abb56e
author_id_fullname_str_mv 4c5e1c0d6f918a2374993b2c5a25d20a_***_Gesu India
cb3b57a21fa4e48ec633d6ba46455e91_***_Simon Robinson
6d662d9e2151b302ed384b243e2a802f_***_Jen Pearson
10b46d7843c2ba53d116ca2ed9abb56e_***_Matt Jones
author Gesu India
Simon Robinson
Jen Pearson
Matt Jones
author2 Gesu India
Martin Grayson
Cecily Morrison
Daniela Massiceti
Simon Robinson
Jen Pearson
Matt Jones
format Conference Paper/Proceeding/Abstract
container_title Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems
container_start_page 1
publishDate 2026
institution Swansea University
isbn 979-8-4007-2278-3
doi_str_mv 10.1145/3772318.3791099
publisher Association for Computing Machinery (ACM)
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description Computer vision systems are increasingly used by blind individuals to navigate their lives, helping, for example, locate objects such as doors or chairs. Yet these recognition systems do not work for many personal objects a blind user might want to find, such as keys or a special notebook. In response, efforts created personalized recognition systems, where individuals train their phones to identify and locate things, like a coffee mug or white cane, using example images/videos. However, these tools are trained on data from high-resource contexts, not necessarily reflecting India’s material culture. This paper discusses the contribution of the ORBIT-India dataset, which extends these tools to the Indian context, home of the world’s largest blind population. The ORBIT-India dataset comprises 105,243 images from 587 videos, representing 76 unique objects. We use this experience to examine dataset collection practices translated from high- to low-resource settings, providing recommendations to support cross-geography dataset collection.
published_date 2026-04-13T11:34:43Z
_version_ 1865250277268914176
score 11.106306

Similar Items