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

2019/06/04 by Satoshi Tsutsui, Dian Zhi, Tsutsui, Satoshi +7 · 1 citation
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Reinforcement Learning in Robotics #Robot Manipulation and Learning #Visual Attention and Saliency Detection

paper · pdf · doi:10.48550/arxiv.1906.01415

openalex publication_date 2019/06/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Prototypical Networks for Few-shot Learning

Cited by

• Egoshots, an ego-vision life-logging dataset and semantic fidelity\n metric to evaluate diversity in image captioning models

Related

• Embodied vision for learning object representations
• Using Motion and Internal Supervision in Object Recognition
• A Computational Account Of Self-Supervised Visual Learning From Egocentric Object Play
• Human Hands as Probes for Interactive Object Understanding
• Systems in development: Motor skill acquisition facilitates three-dimensional object completion.