Saeed Ghorbani

Papers

Total Citations

H-Index

About

Saeed Ghorbani is a researcher at the intersection of computer vision, deep learning, and health monitoring, with a primary focus on pose estimation from unconventional sensing modalities. His most-cited work, "In-Bed Pressure-Based Pose Estimation Using Image Space Representation Learning" (2021, 14 citations), addresses a critical challenge in healthcare technology: estimating human pose from pressure sensor data rather than traditional RGB images. Ghorbani's key contribution lies in developing a novel representation learning framework that bridges the gap between pressure maps and image-space pose models, enabling robust pose estimation even when standard deep learning architectures fail to generalize to pressure-based inputs. This work has direct implications for non-intrusive patient monitoring, sleep quality assessment, and fall detection in clinical and home settings. By tackling the domain shift problem between visual and tactile sensing, Ghorbani has opened new pathways for privacy-preserving health monitoring systems. His research demonstrates a clear trajectory from fundamental computer vision techniques to applied healthcare solutions, making his work relevant for students and researchers interested in embodied AI, sensor fusion, and the translation of deep learning to real-world medical applications.