An attention based dual learning approach for video captioning

Computer Science

• Visual Feature 100%
• Learning Approach 100%
• Video Reconstruction 100%
• Experimental Result 50%
• Visual Informations 50%
• Multimedia 50%
• Learning Mechanism 50%
• semantic gap 50%
• Effective Information 50%
• Multi-Head Attention Mechanism 50%

Keyphrases

• Dual Learning 100%
• Video Captioning 100%
• Raw Video 83%
• Video Caption 83%
• Caption Generation 50%
• Video Reconstruction 33%
• Inception V4 16%