VIIDA and InViDe: computational approaches for generating and evaluating inclusive image paragraphs for the visually impaired.
Journal:
Disability and rehabilitation. Assistive technology
Published Date:
Dec 11, 2024
Abstract
BACKGROUND: Existing image description methods when used as Assistive Technologies often fall short in meeting the needs of blind or low vision (BLV) individuals. They tend to either compress all visual elements into brief captions, create disjointed sentences for each image region, or provide extensive descriptions.