Weijie Sheng
Papers
2
Total Citations
9
H-Index
2
About
Weijie Sheng is a researcher at the forefront of human-centered artificial intelligence, specializing in affective computing, social signal processing, and human–robot interaction. His work focuses on enabling machines to perceive and interpret subtle human cues—such as emotional states and social dynamics—from non-verbal behaviors like gait and spatial positioning. Sheng’s most cited paper, "Data augmentation by separating identity and emotion representations for emotional gait recognition" (2023, 7 citations), introduces a novel framework that disentangles identity and emotion features in walking patterns, significantly improving the robustness of emotion recognition systems. This contribution addresses a critical challenge in affective computing: the confounding influence of individual differences on emotional expression. In another notable study, "A two-branch deep learning with spatial and pose constraints for social group detection" (2023, 2 citations), he proposes an architecture that integrates spatial and pose information to accurately identify social groups in crowded scenes, advancing the field of social robotics. Sheng’s research has direct implications for developing more intuitive and responsive AI systems, and his work is gaining recognition for its innovative approach to bridging the gap between human behavior and machine understanding.
Research Focus
Key Achievements
Top Papers
- 1
- 2