Sheng-Wei Chan
Papers
2
Total Citations
255
H-Index
2
About
Sheng-Wei Chan is a leading researcher in computer vision, with a primary focus on real-time semantic segmentation—a critical technology for autonomous driving and robotics. His major contribution lies in developing efficient deep learning architectures that balance accuracy with computational speed, addressing a key gap in the field where most prior work prioritized precision over inference efficiency. His most influential work, "Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation" (2019), has garnered 228 citations, demonstrating its significant impact on both academic research and practical applications. This paper introduced novel asymmetric convolution modules that dramatically reduce computational cost while maintaining high segmentation quality, enabling real-time performance on resource-constrained platforms. An earlier version of this work (2018, 27 citations) laid the foundation for these innovations. Chan’s research is particularly notable for its direct relevance to industry needs, such as self-driving cars and intelligent robots, where low-latency visual understanding is essential. His achievements highlight a rare ability to drive both theoretical advances and deployable solutions, making him a key figure in the push toward efficient, real-world computer vision systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2