Automatic alt-text: Computer-generated image descriptions for blind users on a social network service

S Wu, J Wieland, O Farivar, J Schiller - … of the 2017 ACM conference on …, 2017 - dl.acm.org
We designed and deployed automatic alt-text (AAT), a system that applies computer vision
technology to identify faces, objects, and themes from photos to generate photo alt-text for …

Toward scalable social alt text: Conversational crowdsourcing as a tool for refining vision-to-language technology for the blind

E Salisbury, E Kamar, M Morris - … of the AAAI Conference on Human …, 2017 - ojs.aaai.org
The access of visually impaired users to imagery in social media is constrained by the
availability of suitable alt text. It is unknown how imperfections in emerging tools for …

Twitter A11y: A browser extension to make Twitter images accessible

C Gleason, A Pavel, E McCamey, C Low… - Proceedings of the …, 2020 - dl.acm.org
Social media platforms are integral to public and private discourse, but are becoming less
accessible to people with vision impairments due to an increase in user-posted images …

Computer vision and conflicting values: Describing people with automated alt text

M Hanley, S Barocas, K Levy, S Azenkot… - Proceedings of the …, 2021 - dl.acm.org
Scholars have recently drawn attention to a range of controversial issues posed by the use
of computer vision for automatically generating descriptions of people in images. Despite …

GenAssist: Making image generation accessible

M Huh, YH Peng, A Pavel - Proceedings of the 36th Annual ACM …, 2023 - dl.acm.org
Blind and low vision (BLV) creators use images to communicate with sighted audiences.
However, creating or retrieving images is challenging for BLV creators as it is difficult to use …

Rich representations of visual content for screen reader users

MR Morris, J Johnson, CL Bennett… - Proceedings of the 2018 …, 2018 - dl.acm.org
Alt text (short for" alternative text") is descriptive text associated with an image in HTML and
other document formats. Screen reader technologies speak the alt text aloud to people who …

ImageExplorer: Multi-layered touch exploration to encourage skepticism towards imperfect AI-generated image captions

J Lee, J Herskovitz, YH Peng, A Guo - … of the 2022 CHI Conference on …, 2022 - dl.acm.org
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 …

The effect of computer-generated descriptions on photo-sharing experiences of people with visual impairments

Y Zhao, S Wu, L Reynolds, S Azenkot - … of the ACM on Human-Computer …, 2017 - dl.acm.org
Like sighted people, visually impaired people want to share photographs on social
networking services, but find it difficult to identify and select photos from their albums. We …

Caption crawler: Enabling reusable alternative text descriptions using reverse image search

D Guinness, E Cutrell, MR Morris - … of the 2018 chi conference on human …, 2018 - dl.acm.org
Accessing images online is often difficult for users with vision impairments. This population
relies on text descriptions of images that vary based on website authors' accessibility …

Regionspeak: Quick comprehensive spatial descriptions of complex images for blind users

Y Zhong, WS Lasecki, E Brady, JP Bigham - Proceedings of the 33rd …, 2015 - dl.acm.org
Blind people often seek answers to their visual questions from remote sources, however, the
commonly adopted single-image, single-response model does not always guarantee …