Memes are a widely popular tool for web users to express their thoughts using visual metaphors. Understanding memes requires recognizing and interpreting visual metaphors with respect to the text inside or around the meme, often while employing background knowledge and reasoning abilities. We present the task of meme captioning and release a new dataset, MemeCap. Our dataset contains 6.3K memes along with the title of the post containing the meme, the meme captions, the literal image caption, and the visual metaphors. Despite the recent success of vision and language (VL) models on tasks such as image captioning and visual question answering, our extensive experiments using state-of-the-art VL models show that they still struggle with visual metaphors, and perform substantially worse than humans.
MemeCap: A Dataset for Captioning and Interpreting Memes
A new dataset, MemeCap, is introduced to address the challenge of captioning memes, which requires understanding visual metaphors, a task at which current vision and language models perform significantly worse than humans.
- Year
- 2023
- Venue
- arXiv 2023
- Authors
- 2
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2305.13703ARXIV-DEFAULT
- TL;DR
- Semantic Scholar