Orbit: A real-world few-shot dataset for teachable object recognition

D Massiceti, L Zintgraf, J Bronskill… - Proceedings of the …, 2021 - openaccess.thecvf.com
Object recognition has made great advances in the last decade, but predominately still relies
on many high-quality training examples per object category. In contrast, learning new …

Mymove: Facilitating older adults to collect in-situ activity labels on a smartwatch with speech

YH Kim, D Chou, B Lee, M Danilovich, A Lazar… - Proceedings of the …, 2022 - dl.acm.org
Current activity tracking technologies are largely trained on younger adults' data, which can
lead to solutions that are not well-suited for older adults. To build activity trackers for older …

Hands holding clues for object recognition in teachable machines

K Lee, H Kacorri - Proceedings of the 2019 CHI conference on human …, 2019 - dl.acm.org
Camera manipulation confounds the use of object recognition applications by blind people.
This is exacerbated when photos from this population are also used to train models, as with …

Exploring machine teaching with children

U Dwivedi, J Gandhi, R Parikh… - … IEEE Symposium on …, 2021 - ieeexplore.ieee.org
Iteratively building and testing machine learning models can help children develop
creativity, flexibility, and comfort with machine learning and artificial intelligence. We explore …

Disability-first dataset creation: lessons from constructing a dataset for teachable object recognition with blind and low vision data collectors

L Theodorou, D Massiceti, L Zintgraf, S Stumpf… - Proceedings of the 23rd …, 2021 - dl.acm.org
Artificial Intelligence (AI) for accessibility is a rapidly growing area, requiring datasets that
are inclusive of the disabled users that assistive technology aims to serve. We offer insights …

Development of species recognition models using Google teachable machine on shorebirds and waterbirds

JJN Wong, N Fadzly - Journal of Taibah University for Science, 2022 - Taylor & Francis
Species identification is an essential ability in every conservation initiative. An efficient and
robust computer vision method was attested with an available online tool with Google's …

Data representativeness in accessibility datasets: A meta-analysis

R Kamikubo, L Wang, C Marte, A Mahmood… - Proceedings of the 24th …, 2022 - dl.acm.org
As data-driven systems are increasingly deployed at scale, ethical concerns have arisen
around unfair and discriminatory outcomes for historically marginalized groups that are …

Understanding Personalized Accessibility through Teachable AI: Designing and Evaluating Find My Things for People who are Blind or Low Vision

C Morrison, M Grayson, RF Marques… - Proceedings of the 25th …, 2023 - dl.acm.org
The opportunity for artificial intelligence, or AI, to enable accessibility is rapidly growing, but
widely impactful applications can be challenging to build given the diversity of user need …

Contributing to Accessibility Datasets: Reflections on Sharing Study Data by Blind People

R Kamikubo, K Lee, H Kacorri - … of the 2023 CHI Conference on Human …, 2023 - dl.acm.org
To ensure that AI-infused systems work for disabled people, we need to bring accessibility
datasets sourced from this community in the development lifecycle. However, there are …

Crowdsourcing the perception of machine teaching

J Hong, K Lee, J Xu, H Kacorri - … of the 2020 CHI Conference on Human …, 2020 - dl.acm.org
Teachable interfaces can empower end-users to attune machine learning systems to their
idiosyncratic characteristics and environment by explicitly providing pertinent training …