John Seon Keun Yi

I am a second-year Computer Science Ph.D student at Boston University.

I received Masters and Bachelors degrees in Computer Science from Georgia Institute of Technology.

Email  /  CV  /  Google Scholar  /  Github

My research interest mainly focuses on using computer vision techniques for robotics and autonomous agents. Particularly, I am interested assistive technologies to improve the lives of disabled individuals.

Continuously learning to drive from an infinite flow of YouTube driving videos.

A comprehensive survey on Masked Autoencoders(MAE) in vision and other fields.

We use simple self-supervised pretext tasks and a loss-based sampler to sample both representative and difficult data from an unlabeled pool.

We use semantic scene graphs to disambiguate referring expressions in an interactive object grounding scenario. This is effectively useful in scenes with multiple identical objects.

We use 2D inpainting methods to complete occlusions and imperfections in 3D building point cloud scans.

An HRI model for a guide dog robot that distinguishes different force commands from the attached harness and reacts by adjusting its movement.

We try to learn domain agnostic generelizable representations that yields good performance on multiple downstream tasks, by leveraging the power of multiple self-supervised pretext tasks. We demonstrate one of the proposed approaches which uses an ensemble of multiple pretext tasks to make final predictions in the downstream tasks.

This page is adapted from this template which is created by Jon Barron.