jane-yang.bsky.social @jane-yang.bsky.social · 16/05/2026Category organization: We found stronger within-superordinate clustering in the child’s view than in a curated dataset (THINGS). We also find this pattern in data from individual children. Maybe this provides a way for children to parse the “blooming buzzing confusion” of their visual world! 171 0
jane-yang.bsky.social @jane-yang.bsky.social · 16/05/2026Content: huge variation in viewpoint & format — including lots of depictions (esp. animals—examples below!!. Children are learning about many categories from these kinds of “child-directed” visuals rather than real-life exemplars. 161 0
jane-yang.bsky.social @jane-yang.bsky.social · 16/05/2026What did we find? First, we found that a few categories dominate — across all domains! Children see some categories much more often than others, replicating prior work. 171 0
jane-yang.bsky.social @jane-yang.bsky.social · 16/05/2026We analyzed the objects in view in 868 hours of egocentric videos from the BabyView dataset—from 31 children (5-36 months old). We used an object detection model to extract object categories from >3M frames—pipeline below. And more about the BabyView Project here! babyview-project.github.io 152 0