Kon Mouzakis

Papers

Total Citations

H-Index

About

Kon Mouzakis is an emerging researcher working at the intersection of computer vision, multi-agent systems, and federated machine learning. His work spans two compelling frontiers of modern artificial intelligence: intelligent object tracking and privacy-preserving distributed learning. In his most-cited contribution, "CSAOT: Cooperative Multi-Agent System for Active Object Tracking" (2025), Mouzakis advances the field of Active Object Tracking by developing a cooperative multi-agent framework that moves beyond the limitations of static camera-based passive tracking — a significant step forward for applications in autonomous navigation, surveillance, and robotics. This work has already attracted early citation attention within the research community. His complementary research on federated and meta-learning approaches tailored to mining operations demonstrates a keen ability to apply cutting-edge machine learning methodologies to real-world industrial challenges, bridging theoretical innovation with practical deployment. Though early in his research career, Mouzakis shows a distinctive breadth of interest, combining perception, autonomy, and decentralized learning. Students and researchers exploring adaptive AI systems, multi-agent coordination, or privacy-conscious machine learning will find his growing body of work a valuable and forward-thinking reference point.