Eli Saber

Papers

Total Citations

H-Index

About

Eli Saber’s research lies at the intersection of computer vision, human-robot interaction, and multimodal machine learning, with a focus on developing intelligent systems that perceive and interact with the physical world. His early work on a ping-pong playing robotic arm (31 citations) demonstrated a novel application of robotic vision, using displaced frame difference (DFD) to segment ball motion from background clutter and 3-D tracking via a single calibrated CCD camera—a practical contribution to real-time visual servoing. More recently, Saber has advanced multimodal fusion networks for aerial imagery (6 citations), tackling the critical issue of modality bias in deep learning. His 2024 paper proposes a framework to regulate how different data sources (e.g., RGB, thermal, LiDAR) contribute to fusion, ensuring that no single modality dominates and that the full potential of multimodal data is realized. This work has immediate relevance for autonomous navigation, surveillance, and remote sensing. With a career spanning foundational robotics to cutting-edge AI, Saber’s research consistently bridges theory and application, making his contributions valuable for students and engineers building perceptive, adaptive systems.