Summary of Eyeformer: Predicting Personalized Scanpaths with Transformer-guided Reinforcement Learning, by Yue Jiang et al.
EyeFormer: Predicting Personalized Scanpaths with Transformer-Guided Reinforcement Learning
by Yue Jiang, Zixin Guo, Hamed Rezazadegan Tavakoli, Luis A. Leiva, Antti Oulasvirta
First submitted to arxiv on: 15 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
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 A novel graphical interface (GUI) scanpath prediction model, EyeFormer, is introduced to predict personalized gaze locations based on a few user-scanpath samples. Leveraging a Transformer architecture as a policy network, EyeFormer uses deep reinforcement learning to control gaze locations and predicts full scanpath information, including fixation positions and duration, across individuals and various stimulus types. This capability enables GUI layout optimization driven by the model. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary EyeFormer is a new computer program that can predict where people look on graphical user interfaces (GUIs) based on some examples of how they looked before. It uses a special kind of artificial intelligence called deep reinforcement learning to do this. The program can also tell us how long people will stay looking at certain things and what order they’ll look in. This is useful for designing GUIs that are easy to use and understand. |
Keywords
» Artificial intelligence » Optimization » Reinforcement learning » Transformer
