Xiangjun Kong

Dalian Maritime University, Sinomach (China)

Papers

Total Citations

H-Index

About

Xiangjun Kong is a leading researcher at the intersection of computer vision, underwater robotics, and multi-agent systems. Their work is defined by two major contributions: pioneering deep learning methods for underwater image enhancement and developing optimization algorithms for multi-robot coordination. In 2023, Kong introduced the Underwater Attentional Generative Adversarial Network (UAGAN), a novel architecture that combines dense feature concatenation with attention mechanisms to selectively suppress underwater noise and prevent over-enhancement—a breakthrough that has already garnered 47 citations. Earlier, in 2019, Kong addressed the complex challenge of heterogeneous multi-robot task allocation by fusing Particle Swarm Optimization with a Greedy Algorithm, achieving near-optimal solutions that minimize execution time while maintaining load balance across diverse robotic resources. That work has accumulated 44 citations and remains influential in swarm robotics. Kong’s research uniquely bridges the gap between perceptual quality in degraded visual environments and efficient autonomous decision-making, offering practical solutions for real-world underwater exploration and collaborative robotics. Their work is essential reading for anyone interested in generative models for image restoration or optimization in multi-agent systems.