Multi-view key information representation and multi-modal fusion for single-subject routine action recognition

• Published in: Applied intelligence (Dordrecht, Netherlands) Vol. 54; no. 4; pp. 3222 - 3244
• Main Authors: Chao, Xin, Ji, Genlin, Qi, Xiaosha
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.02.2024; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Computer Science; Correlation analysis; Energy; Human activity recognition; Lie groups; Machines; Manufacturing; Mechanical Engineering; Methods; Neural networks; Processes; Representations; Multi-view key information representation; Human action recognition; Motion mean normalization; Multi-modal fusion

Currently, human action recognition has witnessed remarkable progress, and its achievements have been applied to daily life. However, most methods extract features from only a single view within each modality, which may not comprehensively capture the diversity and complexity of actions. Moreover, t...