We introduce a novel meme generation system, which given any image can
produce a humorous and relevant caption. Furthermore, the system can be
conditioned on not only an image but also a user-defined label relating to the
meme template, giving a handle to the user on meme content. The system uses a
pretrained Inception-v3 network to return an image embedding which is passed to
an attention-based deep-layer LSTM model producing the caption - inspired by
the widely recognised Show and Tell Model. We implement a modified beam search
to encourage diversity in the captions. We evaluate the quality of our model
using perplexity and human assessment on both the quality of memes generated
and whether they can be differentiated from real ones. Our model produces
original memes that cannot on the whole be differentiated from real ones.

本研究介绍了一种新颖的模因生成系统，该系统可根据给定的任何图像产生幽默而相关的字幕，并且还可以被调节到用户自定义的与模板相关的标签。系统使用预训练的 Inception-v3 网络返回进行字幕生成的图像嵌入，通过基于注意力机制的深度 LSTM 模型实现生成 - 这受到广泛认可的 Show and Tell 模型的启发。研究人员通过困惑度和人工评估对模型进行了质量评估，包括所生成的模因的质量和其与真正的模因的区别。结果表明，我们的模型可以生成与真实模因在整体上无法区分的原创模因。