From Human-Powered to Automated Video Descriptions for Blind and Low Vision Users
Official title: From Human-Powered to Automated Video Description for Blind and Low Vision Users
Funded at Arizona State University-Tempe Campus · NIH-11418912 · Data updated 2026-11-12
A grant to develop AI tools that automatically describe online videos for people who are blind or have low vision, helping them access education, health information, work, and entertainment.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Arizona State University-Tempe Campus NIH-funded |
| Lab location | 1 site (Scottsdale, United States) |
| Project start | July 1, 2023 |
| Project end | June 30, 2028 |
| Funding year | 2026 |
| Award (this year) | $628,962 |
| NIH project number | 5R01EY034562-04 |
| Project ID | NIH-11418912 on NIH RePORTER |
Who could benefit from this research
✓Could help
People with blindness or low vision who rely on video descriptions to access digital content.
✕Less likely to help
Individuals who primarily rely on text or audio content that is already accessible through other means may see limited benefit.
What this research studies
This project aims to create a scalable AI system that can automatically generate audio descriptions for online videos and answer user questions about video content, making digital information more accessible to BLV individuals. The work builds on the YouDescribe platform, which currently relies on volunteers, by adding automated description generation to meet growing demand. It will involve developing algorithms that understand video context, generate accurate descriptions, and respond to user queries, all while considering accessibility and usability for diverse users. The outcome could dramatically reduce wait times for descriptions and broaden access to timely health and safety information delivered through videos.
Why it matters
Potential benefit: If successful, BLV users could access video content quickly and independently, improving education, safety, and participation in daily life.
How similar studies have gone: Preliminary work with YouDescribe demonstrates demand for user-generated descriptions; this project extends it with AI-driven automation to scale access.
Where this research is happening
-
Arizona State University-Tempe Campus
Scottsdale, United States Active
Researchers
- Principal investigator: Fazli, Pooyan — Arizona State University-Tempe Campus
- Study coordinator: Fazli, Pooyan
Related research
Other NIH-funded projects on the same topics.
-
Understanding how herpesviruses move and exit cells (focus on HSV-1 and PRV)
Scientists are studying how herpesviruses travel inside nerve cells and exit at the right spots, which could lead to better prevention and treatment of infections in people and animals.
-
Whole Protein Arrays to Find Antibodies Linked to Islet Autoimmunity in a Big Birth Cohort
This NIH grant aims to map antibodies against many microbes in children from the TEDDY study to understand what infections might be linked to the development of type 1 diabetes.
-
Climate heat and Alzheimer's risk in older adults
Heat exposure may influence brain health and dementia risk in older adults living in the United States.
-
Certified Cancer Registry Extraction with Proof-Certified Trust
A new AI-powered system helps cancer registries extract standardized data from medical records more accurately and with formal proofs to ensure trust.
-
Demystifying E. coli ecosystems with synthetic microbial communities
A project builds controlled, synthetic E. coli communities to uncover how different interactions shape colony behavior and health-related outcomes.
-
Aflatoxin exposure and child growth in Guatemala
A study in rural Guatemala will track how exposure to aflatoxin relates to growth and gut health in young children.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.