We have now entered the era of trillion parameter machine learning models trained on
billion-sized datasets scraped from the internet. The rise of these gargantuan datasets has …

The user study is a fundamental method used in HCI. In designing user studies, we often
use compensation strategies to incentivize recruitment. However, compensation can also …

Many accessibility features available on mobile platforms require applications (apps) to
provide complete and accurate metadata describing user interface (UI) components …

While an important problem in the vision community is to design algorithms that can
automatically caption images, few publicly-available datasets for algorithm development …

Content creators are instructed to write textual descriptions of visual content to make it
accessible; yet existing guidelines lack specifics on how to write about people's appearance …

Access to digital images is important to people who are blind or have low vision (BLV). Many
contemporary image description efforts do not take into account this population's nuanced …

Image descriptions are how people who are blind or have low vision (BLV) access
information depicted within images. To our knowledge, no prior work has examined how a …

Blind users rely on alternative text (alt-text) to understand an image; however, alt-text is often
missing. AI-generated captions are a more scalable alternative, but they often miss crucial …

Visual question answering (VQA) has the potential to make the Internet more accessible in
an interactive way, allowing people who cannot see images to ask questions about them …

Natural language descriptions of user interface (UI) elements such as alternative text are
crucial for accessibility and language-based interaction in general. Yet, these descriptions …