Self-supervised Representation Learning

Location of research: Hybrid (both Remote and On Site)

We are sorry, this position has been filled.

Our group studies computer vision and machine learning. By training machines to observe and interact with their surroundings, we aim to create robust and versatile models for perception. We investigate visual models that capitalize on large amounts of unlabeled data and transfer across tasks and modalities. This project will study how to learn video representation models, and apply them to various domains, such as health and robotics.

Lab: Columbia Computer Vision lab

Direct Supervisor: Carl Vondrick

Position Dates: 6/1/2021 - 9/1/2021

Hours per Week: 30

Paid Position: Yes

Credit: Yes

Qualifications: Deep Learning, Linear Algebra

Eligibility: Sophomore, Junior, Senior, Master's (SEAS only)

Carl Vondrick, [email protected]