Papers
2
Total Citations
6
H-Index
2
About
Xing Peng is an emerging researcher specializing in computer vision and deep learning, with a particular focus on underwater object detection and real-time visual perception systems. Their work addresses one of the most technically demanding frontiers in applied AI: reliable target recognition in challenging underwater environments characterized by optical attenuation, light scattering, low illumination, and turbidity — conditions that render conventional detection methods inadequate. Peng's most notable contributions include the development of YOLOv11-MSE, a lightweight network incorporating multi-scale dilated attention mechanisms designed to improve detection accuracy for densely distributed small underwater targets, and DyAqua-YOLO, a high-precision real-time detection model built on a dynamic adaptive architecture tailored for turbid and spectrally degraded aquatic settings. Both works demonstrate a commitment to balancing computational efficiency with robust real-world performance — a critical requirement for deployment in underwater robotics and autonomous marine inspection systems. Though early in their publishing career, Peng's research has already garnered attention within the marine technology and computer vision communities, accumulating citations that reflect growing interest in practical AI solutions for ocean exploration, marine resource management, and ecological monitoring. Their contributions position them as a promising voice in intelligent underwater perception research.
Research Focus
Key Achievements
Top Papers
- 1
- 2