Summary of Is Ai Fun? Humordb: a Curated Dataset and Benchmark to Investigate Graphical Humor, by Veedant Jain and Felipe Dos Santos Alves Feitosa and Gabriel Kreiman
Is AI fun? HumorDB: a curated dataset and benchmark to investigate graphical humor
by Veedant Jain, Felipe dos Santos Alves Feitosa, Gabriel Kreiman
First submitted to arxiv on: 19 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper tackles the complex challenge of understanding humor in visual scenes, which is crucial for developing AI systems that can comprehend and create humor. The authors introduce HumorDB, a novel image-only dataset designed to advance our understanding of visual humor. This dataset consists of meticulously curated image pairs with contrasting humor ratings, highlighting subtle visual cues that trigger humor. The paper enables evaluation through various tasks, including binary classification, range regression, and pairwise comparison, effectively capturing the subjective nature of humor perception. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is all about making computers understand what’s funny! Right now, AI can’t really get humor, but the authors created a special dataset called HumorDB to help with this problem. They took lots of pictures and paired them up based on how funny they are (or aren’t). This lets researchers test their computer programs to see if they can tell which picture is funnier. The results are pretty cool, and it looks like computers that understand both images and words do a lot better at getting humor than those that only look at pictures. |
Keywords
» Artificial intelligence » Classification » Regression
