# Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Study

arXiv: https://arxiv.org/abs/1906.01415 · HTML: https://mlsanity.com/paper/1906.01415/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2019.

## Built on by (most cited first, 1 of 1)

- [Reverse-engineer the Distributional Structure of Infant Egocentric Views for Training Generalizable Image Classifiers](https://mlsanity.com/paper/2106.06694/) (2021)

## Abstract (arXiv)

Inspired by the remarkable ability of the infant visual learning system, a recent study collected first-person images from children to analyze the `training data' that they receive. We conduct a follow-up study that investigates two additional directions. First, given that infants can quickly learn to recognize a new object without much supervision (i.e. few-shot learning), we limit the number of training images. Second, we investigate how children control the supervision signals they receive during learning based on hand manipulation of objects. Our experimental results suggest that supervision with hand manipulation is better than without hands, and the trend is consistent even when a small number of images is available.