Xiaoxia Wen
Papers
1
Total Citations
29
H-Index
1
About
Xiaoxia Wen is a researcher at the forefront of precision agriculture and deep learning, specializing in lightweight computer vision models for real-time field applications. Her most impactful work, "YOLOv8-ECFS: A lightweight model for weed species detection in soybean fields" (2024), has already garnered 29 citations, reflecting its immediate relevance to sustainable farming. Wen’s key contribution lies in optimizing the YOLOv8 architecture with efficient channel and feature selection mechanisms, drastically reducing computational overhead while maintaining high detection accuracy for diverse weed species. This innovation addresses a critical bottleneck in deploying AI on resource-constrained edge devices, enabling farmers to implement targeted herbicide application and reduce environmental waste. Beyond this flagship study, Wen’s research portfolio spans crop phenotyping, transfer learning for agricultural datasets, and real-time pest monitoring. Her work is notable for bridging the gap between cutting-edge computer vision and practical agricultural needs, earning recognition from both the AI and agronomy communities. By prioritizing model efficiency without sacrificing performance, Wen is helping democratize smart farming technologies, making them accessible to smallholder farms and large-scale operations alike.
Research Focus
Key Achievements
Top Papers
- 1