KHFA: Knowledge-Driven Hierarchical Feature Alignment Framework for Subject-Invariant Facial Action Unit Detection

• Published in: IEEE transactions on instrumentation and measurement Vol. 73; pp. 1 - 14
• Main Authors: Zhao, Huijuan, He, Shuangjiang, Du, Congju, Liu, Linyun, Yu, Li
• Format: Journal Article
• Language: English
• Published: New York IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Affective computing; Alignment; Attention mechanisms; Coherence; Contrastive learning; Contrastive learning (CL); Correlation; Facial muscles; Feature extraction; hierarchical feature alignment; hybrid attention mechanism; Invariants; multilevel knowledge; Muscles; Physiological effects; Semantics; subject-invariant facial action unit (AU) detection

Facial action unit (AU) detection constitutes precise measurements for facial appearance variances, holding great significance within the realms of affective computing, human-computer interaction, and negotiation. Subject-invariant AU detection remains a challenge primarily due to the distribution v...