Subconscious Micro-behavior Analysis

Integrating psychological theories of non-conscious behaviors

Our research in subconscious micro-behavior analysis focuses on understanding and interpreting involuntary, subtle bodily movements that reveal genuine emotional states. These micro-behaviors occur outside conscious control and provide authentic cues about a person's true emotional and psychological state.

Research Focus: Developing identity-free artificial emotional intelligence through comprehensive micro-gesture understanding, enabling privacy-preserving emotion analysis without personal identification.

Key Contributions

  • Identity-free AI Emotion Intelligence: Pioneering frameworks for emotion analysis without personal identification
  • iMiGUE Dataset: First identity-free video dataset for micro-gesture understanding and emotion analysis
  • MSF-Mamba Framework: Motion-aware state fusion with Mamba architecture for efficient micro-gesture recognition
  • MGMILA Method: Eulerian motion-aware MILA for advanced micro-gesture recognition
  • SMG Dataset: Comprehensive dataset for spontaneous body gestures in emotional stress state analysis
Identity-free Artificial Emotional Intelligence via Micro-Gesture Understanding
R. Gao, X. Liu*, B. Xing, Z. Yu, B. W. Schuller, and H. Kälviäinen
IEEE Transactions on Affective Computing, 2025
iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis
X. Liu, H. Shi, H. Chen, Z. Yu, X. Li, and G. Zhao
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10631-10642, 2021
project page
MSF-Mamba: Motion-aware State Fusion Mamba for Efficient Micro-Gesture Recognition
D. Li, J. Shao, B. Xing, R. Gao, B. Wen, H. Kälviäinen, and X. Liu*
IEEE Transactions on Multimedia, 2025
MGMILA: Eulerian Motion-Aware MILA for Micro-Gesture Recognition
B. Xing, D. Li, R. Gao, X. Liu*, and H. Kälviäinen
Machine Intelligence Research, 2025
SMG: A Micro-Gesture Dataset Towards Spontaneous Body Gestures for Emotional Stress State Analysis
H. Chen, H. Shi, X. Liu, X. Li, and G. Zhao
International Journal of Computer Vision (IJCV), 2023
« Back to Research Framework