RESEARCH PAPERSubmitted 9 Apr 2026

ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration

Yanwen Zou; Chenyang Shi; Wenye Yu; Han Xue; Jun Lv; Ye Pan; Chuan Wen; Cewu Lu

Classification

Major category: Datasets
Quadrant: Not applicable
Architecture: Not applicable
Prediction paradigm: Not applicable
Subcategories: Datasets & data collection Human egocentric data Data collection interfaces
Source review status: Verified from primary sources

Category review. ActiveGlasses introduces an active-vision human-demonstration collection and transfer system with aligned stereo/head/object trajectories. Its concrete supervision interface belongs with data collection; its two trajectory policy heads do not model future environmental dynamics. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX

@article{activeglasses,
      title={ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration}, 
      author={Yanwen Zou and Chenyang Shi and Wenye Yu and Han Xue and Jun Lv and Ye Pan and Chuan Wen and Cewu Lu},
      year={2026},
      journal={arXiv:2604.08534},
}

Classification

Contribution

Abstract

Affiliations

BibTeX

More in this category

Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video Generation

HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone

How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning