Teaching Yourself: A Self-Knowledge Distillation Approach to Action Recognition

Computer Science

• Action Recognition 100%
• Backbone Network 16%
• Data Diversity 16%
• Experimental Result 16%
• human action recognition 16%
• Knowledge Distillation 100%
• Neural Network 16%
• Recognition Performance 16%
• Residual Neural Network 16%
• Semisupervised Learning 16%
• Supervised Learning 16%
• Training Process 16%

Keyphrases

• Consistent Prediction 50%
• Knowledge Distillation 25%
• Knowledge Distillation Method 75%
• Student Network 25%