mlsanityData to 14 Oct 2026

Reverse-engineer the Distributional Structure of Infant Egocentric Views for Training Generalizable Image Classifiers

arXiv 2106.06694 ↗First posted 12 Jun 2021cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We analyze egocentric views of attended objects from infants. This paper shows 1) empirical evidence that children's egocentric views have more diverse distributions compared to adults' views, 2) we can computationally simulate the infants' distribution, and 3) the distribution is beneficial for training more generalized image classifiers not only for infant egocentric vision but for third-person computer vision.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 3 of its 6 references that are in the map. First posted on arXiv 12 Jun 2021.

Builds on

3 of 6 references.

References · 3

  1. 2020Self-supervised learning through the eyes of a childcited by 61
  2. 2020A Computational Model of Early Word Learning from the Infant's Point of Viewcited by 6
  3. 2019Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Studycited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Toddlers' Active Gaze Behavior Supports Self-Supervised Object Learningcited by 0