Papers
1
Total Citations
2
H-Index
1
About
Xiuhe Li is a researcher advancing the frontiers of computer vision, with a primary focus on multimodal feature fusion for pedestrian detection. His most cited work, "GLNet-YOLO: Multimodal Feature Fusion for Pedestrian Detection" (2025), addresses a critical challenge in intelligent surveillance and autonomous driving: the limitations of single-modal imaging in complex environments. By integrating complementary data sources, Li's framework enhances detection robustness where traditional methods falter—such as low light or occlusion. Although early in its citation trajectory with 2 citations, this paper signals a promising contribution to safer, more reliable perception systems. Li’s research holds practical implications for robot navigation and smart city infrastructure, bridging the gap between theoretical multimodal learning and real-world deployment. His work exemplifies a growing trend toward fusion-based architectures that leverage diverse sensor inputs, positioning him as an emerging voice in applied computer vision. For students and researchers exploring pedestrian detection or multimodal systems, Li’s approach offers a compelling case study in balancing accuracy and efficiency for dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1GLNet-YOLO: Multimodal Feature Fusion for Pedestrian Detection2 citations · 2025