Workshop: Learning Representations with Limited Supervision

Overview

We are hoping to organize the next version of this workshop in Arizona as part of IEEE BigData 2026 with the same title.

This workshop explores cutting-edge techniques in representation learning with minimal labels. It welcomes contributions on self-supervised learning, transfer learning, in-context learning, active learning, foundation models, and applications to domains with limited labeled data such as underwater imaging, remote sensing, environmental monitoring, and medical imaging.

Paper Submission

Please submit a full-length paper (up to 10 page IEEE 2-column format, reference pages counted in the 10 pages) through the direct submission link or via the main IEEE BigData 2026 Submission Portal.

Papers should be formatted to IEEE Computer Society Proceedings Manuscript Formatting Guidelines. You can download the formatting templates here:

Participate in 2026

If you are interested in participating in the 2026 workshop in any capacity, please fill out the form below:

Organizing Committee

Program Chair

Shaif Chowdhury, Assistant Professor, Texas A&M University–Kingsville, USA

Program Committee (Tentative)

Shaif Chowdhury, Assistant Professor, Texas A&M University–Kingsville, USA
Tarek Mahmud, Assistant Professor, Texas A&M University–Kingsville, USA
Mohammed Javed, Associate Professor, Computer Vision & Biometrics Lab (CVBL), IIIT Allahabad, India
Firas Al-Hindawi, Assistant Professor, King Fahd University of Petroleum & Minerals (KFUPM), Saudi Arabia
Bulla Rajesh, Assistant Professor, IIIT Sri City, India
Suvadeep Roy, PhD Student, Baylor University, USA