Kostantinos Charalampous

Papers

Total Citations

H-Index

About

Kostantinos Charalampous is a researcher whose work bridges computer vision and machine learning, with a focus on human pose estimation and 3D reconstruction. His key contributions lie in developing efficient methods for modeling and analyzing human motion, particularly through sparse representations. His most cited work, "Sparse pose manifolds" (2014), introduces a novel approach to representing human poses as points on low-dimensional manifolds, enabling robust and computationally efficient pose estimation from limited data. This work has garnered 7 citations, reflecting its foundational role in advancing sparse modeling techniques for motion analysis. Charalampous’s research has implications for applications in robotics, animation, and human-computer interaction, where accurate and real-time pose tracking is critical. His work is notable for its emphasis on reducing computational complexity while maintaining high accuracy, making it accessible for practical deployment. By integrating sparse coding with manifold learning, Charalampous has contributed to a deeper understanding of how to leverage data efficiency in vision systems, inspiring further exploration into lightweight yet powerful pose estimation frameworks.