首页 > 其他分享> > [Paper Reading] Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
[Paper Reading] Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
作者:互联网
论文链接:https://arxiv.org/pdf/1502.03044.pdf
代码链接:https://github.com/kelvinxu/arctic-captions & https://github.com/yunjey/show-attend-and-tell & https://github.com/jazzsaxmafia/show_attend_and_tell.tensorflow
主要贡献
在这篇文章中,作者将“注意力机制(Attention Mechanism)”引入了神经机器翻译(Neural Image Captioning)领域,提出了两种不同的注意力模型:‘Soft’ Deterministic Attention Mechanism & ‘Hard’ Stochastic Attention Mechanism。下图展示了Show, Attend and Tell模型的整体框架。
- Stochastic 'Hard' Attention
- Deterministic 'Soft' Attention
实验细节
标签:github,Attend,Neural,Attention,Mechanism,https,show,com 来源: https://www.cnblogs.com/zlian2016/p/10987263.html