Memeify: A Large-Scale Meme Generation System
This work addresses meme generation for researchers and users interested in automated content creation, but it is incremental as it builds on existing transformer models and dataset curation methods.
The authors tackled the problem of meme generation by creating a large-scale dataset of 1.1 million meme captions across 128 classes and themes, and developed a transformer-based system called Memeify that includes a web interface and qualitative user evaluation.
Interest in the research areas related to meme propagation and generation has been increasing rapidly in the last couple of years. Meme datasets available online are either specific to a context or contain no class information. Here, we prepare a large-scale dataset of memes with captions and class labels. The dataset consists of 1.1 million meme captions from 128 classes. We also provide reasoning for the existence of broad categories, called "themes" across the meme dataset; each theme consists of multiple meme classes. Our generation system uses a trained state-of-the-art transformer-based model for caption generation by employing an encoder-decoder architecture. We develop a web interface, called Memeify for users to generate memes of their choice, and explain in detail, the working of individual components of the system. We also perform a qualitative evaluation of the generated memes by conducting a user study. A link to the demonstration of the Memeify system is https://youtu.be/P_Tfs0X-czs.