VIIDA and InViDe: computational approaches for generating and evaluating inclusive image paragraphs for the visually impaired.
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 exten...
| Publicado en: | Disability & Rehabilitation: Assistive Technology Vol. 20; no. 5; pp. 1470 - 1496 |
|---|---|
| Autores principales: | , , , |
| Formato: | algorithm equations & formulas pictorial research tables/charts Journal Article |
| Publicado: |
Taylor & Francis Ltd
Jul2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |