Time-Series Representation Feature Refinement with a Learnable Masking Augmentation Framework in Contrastive Learning

Computer Science

• Contrastive Learning 100%
• Time Series Data 66%
• Temporal Feature 33%
• Learning Framework 33%
• Task Performance 33%
• Baseline Method 33%
• Performance Gain 33%
• Representation Learning 33%
• Human Activity Recognition 33%
• Self-Supervised Learning 33%
• Multiple Time Series 33%
• Feature Extraction 33%

Keyphrases

• UCI HAR 33%
• Dependency Extraction 33%