Chenyun Xiong
Papers
2
Total Citations
44
H-Index
2
About
Chenyun Xiong is a computer vision researcher whose work centers on semantic scene understanding, with a particular focus on RGB-D semantic segmentation for robotic perception systems. Their most prominent contribution lies in developing efficient deep learning architectures that intelligently fuse spatial and depth information to enable accurate environmental recognition — a capability critical for mobile robots navigating real-world scenes. Xiong's signature work, the Spatial Information-Guided Adaptive Context-Aware Network (SIGACNet), addresses a core challenge in RGB-D segmentation: how to effectively leverage geometric depth cues alongside conventional color information without sacrificing computational efficiency. By designing adaptive context-aware mechanisms that respond to spatial relationships between objects and scenes, this research advances the practical deployment of segmentation models on resource-constrained robotic platforms. The work has garnered notable recognition within the research community, accumulating over 40 citations since its 2023 publication, reflecting its relevance to the rapidly growing field of embodied AI and autonomous systems. Xiong's contributions sit at the intersection of efficient network design and multimodal perception, making their research particularly valuable for students and engineers working on real-time robotic vision, autonomous navigation, and intelligent scene analysis.
Research Focus
Key Achievements
Top Papers
- 1
- 2