Sign in

jane-yang.bsky.social

@jane-yang.bsky.social
51 followers 26 following 6 posts

PhD student in the Visual Learning Lab @ UC San Diego advised by Dr. Bria Long. Studying how infants & children learn visual object representations from naturalistic experience. 🔗 janeyang07.github.io

PostsRepliesMedia
jane-yang.bsky.social @jane-yang.bsky.social · 16/05/2026
I’m giving a talk on this at #VSS2026: Sun May 17, 8:30am, Talk Room 2 (Object Recognition, 31.22). My first VSS! www.visionsciences.org/talk-session... Thanks to coauthors @tarunsepuri.bsky.social @alvinwmtan.bsky.social, @khaiaw.bsky.social, @mcxfrank.bsky.social, and @brialong.bsky.social!
visionsciences.org
VSS Talk SessionsTalk Sessions – Vision Sciences Society
0102
jane-yang.bsky.social @jane-yang.bsky.social · 16/05/2026
Category 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
jane-yang.bsky.social @jane-yang.bsky.social · 16/05/2026
Content: 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
jane-yang.bsky.social @jane-yang.bsky.social · 16/05/2026
What 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
jane-yang.bsky.social @jane-yang.bsky.social · 16/05/2026
We 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
jane-yang.bsky.social @jane-yang.bsky.social · 16/05/2026
Children acquire object category representations from their everyday experiences in the first few years of life. What do the inputs to this learning process actually look like? New preprint! arxiv.org/abs/2605.14990
arxiv.org
Characterizing the visual representation of objects from the child's view
Children acquire object category representations from their everyday experiences in the first few years of life. What do the inputs to this learning process look like? We analyzed first-person videos ...
39832