- Attend to You: Personalized Image Captioning with Context Sequence Memory Networks. In CVPR, 2017. [paper] [code]
- Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning [paper] [pytorch] [torch]
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention(ICML2015). [paper] [code] [Tensorflow]