3D HUMAN MOTION GENERATION FROM THE TEXT VIA GESTURE ACTION CLASSIFICATION AND THE AUTOREGRESSIVE MODEL

Keyphrases

• Autoregressive Model 100%
• 3D Human Motion Generation 100%
• Action Classification 100%
• Text Classification Model 66%
• Token 33%
• Generalization Performance 33%
• Human Thinking 33%
• Unit-based 33%
• Classification Datasets 33%
• Generation Model 33%
• Action-based 33%
• Embedding Space 33%
• Data Augmentation 33%
• Deep Learning Model 33%
• Gated Recurrent Unit 33%
• Pre-trained Language Model 33%
• 3D Human Motion 33%
• Nodding 33%
• Gesture Dataset 33%
• Action Recognition Dataset 33%
• Cross-dataset Generalization 33%

Computer Science

• Human Motions 100%
• Classification Action 100%
• Text Classification 50%
• Classification Models 50%
• Generalization Performance 25%
• Variable Length 25%
• Language Modeling 25%
• Generation Model 25%
• Action Recognition 25%
• Embedding Space 25%
• Data Augmentation 25%
• Human Thinking 25%
• Deep Learning Method 25%