Shih-Chung Hsu

Papers

Total Citations

H-Index

About

Shih-Chung Hsu is a leading researcher at the intersection of computer vision and human-robot interaction (HRI), with a primary focus on enabling machines to perceive and understand humans in real-world settings. His work centers on two critical challenges: robust human object identification and accurate facial expression recognition (FER). In his highly cited 2018 paper (40 citations), Hsu proposed a groundbreaking method for human object identification using a simplified Fast Region-based Convolutional Network (Fast R-CNN). This approach achieved state-of-the-art performance on major pedestrian datasets, addressing the practical need for reliable human detection in dynamic environments. Complementing this, his 2017 work on FER for HRI (20 citations) tackled the non-trivial problem of individual variability in emotional expression, developing systems that allow assistant robots to recognize human emotions during close interactions. Hsu’s contributions are foundational for creating socially aware robots that can both detect and respond to human presence and emotional states, directly advancing the safety and naturalness of human-robot collaboration. His research continues to influence the development of intuitive, perceptive robotic systems for assistive and interactive applications.