（四十七）：Supervised Multimodal Bitransformers for Classifying Images and Text

（四十七）：Supervised Multimodal Bitransformers for Classifying Images and Text

• Abstract
• 1 Introduction
• 2 Multimodal Bitransformers
• • 2.1 Image Encoder
  • 2.2 Multimodal Transformer Input Layer
  • 2.3 Classification
  • 2.4 Pre-training
  • 2.5 Fine-tuning
• 4 Results
• 6 Conclusion