# Dank Learning: Generating Memes Using Deep Neural Networks

arXiv: https://arxiv.org/abs/1806.04510 · HTML: https://mlsanity.com/paper/1806.04510/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2018.

## Built on by (most cited first, 10 of 10)

- [XMeCap: Meme Caption Generation with Sub-Image Adaptability](https://mlsanity.com/paper/2407.17152/) (2024)
- [OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?](https://mlsanity.com/paper/2307.11636/) (2023)
- [A Template Is All You Meme](https://mlsanity.com/paper/2311.06649/) (2023)
- [MemeCraft: Contextual and Stance-Driven Multimodal Meme Generation](https://mlsanity.com/paper/2403.14652/) (2024)
- [Multimodal Analysis of memes for sentiment extraction](https://mlsanity.com/paper/2112.11850/) (2021)
- [Humor in Pixels: Benchmarking Large Multimodal Models Understanding of Online Comics](https://mlsanity.com/paper/2509.12248/) (2025)
- [Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis](https://mlsanity.com/paper/2209.14667/) (2022)
- [Large Vision-Language Models for Knowledge-Grounded Data Annotation of Memes](https://mlsanity.com/paper/2501.13851/) (2025)
- [Clustering Internet Memes Through Template Matching and Multi-Dimensional Similarity](https://mlsanity.com/paper/2505.00056/) (2025)
- [From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme](https://mlsanity.com/paper/2512.24555/) (2025)

## Abstract (arXiv)

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.