Summary of Generation and Detection Of Sign Language Deepfakes – a Linguistic and Visual Analysis, by Shahzeb Naeem et al.
Generation and Detection of Sign Language Deepfakes – A Linguistic and Visual Analysis
by Shahzeb Naeem, Muhammad Riyyan Khan, Usman Tariq, Abhinav Dhall, Carlos Ivan Colon, Hasan Al-Nashash
First submitted to arxiv on: 1 Apr 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 research paper explores the potential benefits of deepfake technology in generating sign language videos for the Deaf and Hard of Hearing (DHoH) community. The generated videos are vetted by a sign language expert to ensure accuracy, using a dataset consisting of over 1200 videos featuring both seen and unseen individuals. Computer vision and natural language processing models evaluate the technical and visual credibility of the dataset, while linguistic analysis reveals that the interpretation of generated videos is at least 90% similar to authentic sign language. Visual analysis demonstrates the ability to produce convincingly realistic deepfakes for new subjects using a pose/style transfer model. The study also contributes to the detection of fraudulent sign language videos by establishing a baseline for deepfake detection on this dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research paper is about using computer technology called “deepfakes” to create fake videos that look and act like real sign language. The goal is to help people who are Deaf or Hard of Hearing communicate better with others. The study creates a big collection of sign language videos and uses special algorithms to check how well the fake videos match what real sign language looks like. It also finds ways to spot fake sign language videos that might be trying to trick people. |
Keywords
» Artificial intelligence » Natural language processing » Style transfer
