（六十）：Show, Attend and Tell Neural Image Caption Generation with Visual Attention

（六十）：Show, Attend and Tell Neural Image Caption Generation with Visual Attention

• Abstract
• 1. Introduction
• 2. Related Work
• 3. Image Caption Generation with Attention Mechanism
• • 3.1. Model Details
  • • 3.1.1. ENCODER: CONVOLUTIONAL FEATURES
    • 3.1.2. DECODER: LONG SHORT-TERM MEMORY NETWORK
• 4. Learning Stochastic “Hard” vs Deterministic “Soft” Attention
• • 4.1. Stochastic “Hard” Attention 随机“硬”的关注<