Papers
6
Total Citations
379
H-Index
5
About
Wujie Zhou is a computer vision researcher whose work centers on multimodal semantic segmentation, scene understanding, and deep learning for robotic and autonomous systems. His research primarily addresses the fusion of complementary data modalities — including RGB-thermal, RGB-D, and depth imaging — to enable robust visual perception in challenging real-world environments such as urban roads, indoor spaces, and unstructured wild scenes. Zhou's most influential contribution, "GMNet: Graded-Feature Multilabel-Learning Network for RGB-Thermal Urban Scene Semantic Segmentation" (2021), has accumulated over 318 citations, establishing him as a leading voice in cross-modal fusion for autonomous driving and surveillance applications. His subsequent work spans cascaded network architectures (THCANet), lightweight efficient models suitable for mobile deployment, knowledge distillation techniques, and mirror segmentation — a particularly difficult perceptual challenge. His 2025 work on state space modeling reflects his engagement with emerging computational paradigms to reduce overhead in real-time multimodal processing. Collectively, Zhou's research addresses a critical bottleneck in robotics and autonomous navigation: making scene understanding both accurate and computationally feasible across diverse sensor inputs, making his contributions highly relevant to researchers advancing embodied AI and intelligent systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6