Linjie Wang
Papers
1
Total Citations
65
H-Index
1
About
Linjie Wang is a leading researcher in computer vision and multimedia signal processing, with a primary focus on lightweight semantic segmentation for real-world applications. Her most-cited work, "Boundary-Guided Lightweight Semantic Segmentation With Multi-Scale Semantic Context" (2024, 65 citations), addresses a critical challenge in deploying deep learning on resource-constrained devices. By introducing a novel dual-resolution architecture that integrates boundary-aware guidance with multi-scale semantic context, Wang’s method achieves state-of-the-art accuracy while maintaining computational efficiency—a breakthrough for autonomous driving, robotic vision, and virtual reality systems. Her contributions have garnered significant attention for balancing performance and practicality, enabling high-quality image understanding in edge-computing environments. Wang’s research is distinguished by its focus on bridging the gap between academic model design and industrial deployment, making her work highly cited among practitioners seeking efficient solutions. Her achievements underscore a commitment to advancing multimedia applications where real-time, accurate segmentation is paramount, positioning her as a key innovator in lightweight vision architectures.
Research Focus
Key Achievements
Top Papers
- 1