Sabera Hoque

Papers

Total Citations

H-Index

About

Sabera Hoque is a researcher at the forefront of computer vision and machine learning, whose work bridges 3D perception and data-centric AI. Her most impactful contribution, "A Comprehensive Review on 3D Object Detection and 6D Pose Estimation With Deep Learning" (2021, 83 citations), has become a key reference in the field, synthesizing deep learning approaches for understanding object size, position, and orientation in three-dimensional space. This review has guided researchers and practitioners working on robotics, augmented reality, and autonomous systems. Beyond 3D vision, Hoque tackles the fundamental challenge of imbalanced data in supervised learning. Her paper "Advanced Data Balancing Method with SVM Decision Boundary and Bagging" (2019) proposes a novel ensemble technique that integrates Support Vector Machines with bagging to improve classification performance on skewed datasets—a critical issue in real-world applications like fraud detection and medical diagnosis. By addressing both high-level visual understanding and the practical hurdles of training robust models, Hoque demonstrates a rare ability to advance theory while solving applied problems. Her work continues to influence how machines perceive the physical world and learn from imperfect data.