（五十七）：Deep Modular Co-Attention Networks for Visual Question Answering
- Abstract
- 1. Introduction
- 2. Related Work
-
- ==视觉问答(VQA)==
- ==Co-Attention模型==
- 3. Modular Co-Attention Layer
-
- 3.1. Self-Attention and Guided-Attention Units
- 3.2. Modular Composition for VQA
- 4. Modular Co-Attention Networks
-
- 4.1. Question and Image Representations 问题与图像表示