Hsueh‐Ming Hang
Papers
2
Total Citations
255
H-Index
2
About
Hsueh‐Ming Hang is a leading figure in computer vision and image processing, whose work has profoundly shaped real-time semantic segmentation—a critical technology for autonomous driving and robotics. His most influential contribution, the development of Efficient Dense Modules of Asymmetric Convolution (EDANet), has garnered over 255 citations across its 2018 and 2019 publications. This breakthrough directly addressed a key challenge in the field: balancing high estimation accuracy with computational efficiency. While many prior studies prioritized accuracy at the expense of speed, Hang’s innovative architecture enabled fast, high-quality segmentation without sacrificing real-time performance. His research has provided a practical foundation for deploying deep learning models in resource-constrained environments, making him a pivotal figure in bridging the gap between academic theory and industrial application. Beyond this landmark work, Hang’s broader contributions to multimedia signal processing and video coding have established him as a respected authority. His ability to identify and solve pressing efficiency bottlenecks continues to inspire new generations of researchers aiming to build faster, smarter, and more deployable computer vision systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2