Liang-Chieh Chen

Papers

Total Citations

H-Index

About

Liang-Chieh Chen is a leading researcher in computer vision, with a primary focus on semantic and panoptic segmentation—critical tasks for machine perception in robotics and autonomous driving. His work has significantly advanced the field by developing efficient, high-performance models that can classify every pixel in an image and simultaneously identify object instances. Notably, Chen contributed to the "Waymo Open Dataset: Panoramic Video Panoptic Segmentation" (2022), a landmark dataset that has garnered over 55 citations, providing a benchmark for panoramic video understanding. He also pioneered "Superpixel Transformers for Efficient Semantic Segmentation" (2023), which introduces a novel approach to reduce computational complexity while maintaining accuracy, addressing the high-dimensionality challenge of pixel-level classification. With over 69 total citations from his most-cited works, Chen's research bridges the gap between theoretical innovation and practical deployment, particularly in autonomous driving systems. His contributions to efficient segmentation architectures and large-scale datasets have made him a key figure in advancing real-world machine perception, inspiring both academic and industrial applications.