Everyday sights that help babies learn words
Grounding models of category learning in the visual experiences of young children
This project uses photos taken from a baby's point of view and computer models to learn how young children's everyday visual experiences shape the categories behind early word learning.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of California, San Diego NIH-funded |
| Lab location | 1 site (La Jolla, United States) |
| Project ID | NIH-11192360 on NIH RePORTER |
What this research studies
As a parent, you would be asked to report which objects your child sees often and to provide photos taken from the child's viewpoint. Researchers will build a representative dataset of these infant-view images and feed them into deep neural networks to model how children form visual categories. They will compare learning from infant-like visual diets to models trained on typical adult photos and look for links between visual experience differences and which words children learn early. The work aims to explain how ordinary daily sights help toddlers generalize category labels like “dog” across different examples.
Who could benefit from this research
Good fit: Ideal candidates are infants and toddlers (and their caregivers) willing to provide brief parent-report information and photos taken from the child's perspective.
Not a fit: Older children or adults with no involvement in early word learning, and families unwilling or unable to share photos or reports, would not benefit from participating.
Why it matters
Potential benefit: If successful, this work could inform better ways to support early language development and help identify children at risk for language delays.
How similar studies have performed: Previous studies have used head-camera images and computational models for infant vision, but combining a representative infant-view dataset with deep neural networks to link visual experience directly to early word learning is a newer approach.
Where this research is happening
La Jolla, United States
- University of California, San Diego — La Jolla, United States (Active)
Researchers
- Principal investigator: Long, Bria — University of California, San Diego
- Study coordinator: Long, Bria
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 below.