Summary of Tpp-gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes, by Alessandro D’amelio et al.
TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes
by Alessandro D’Amelio, Giuseppe Cartella, Vittorio Cuculo, Manuele Lucchi, Marcella Cornia, Rita Cucchiara, Giuseppe Boccignone
First submitted to arxiv on: 30 Oct 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 The paper introduces TPP-Gaze, a novel approach to model scanpath dynamics in visual attention, which jointly learns the temporal dynamics of fixation position and duration. The authors leverage Neural Temporal Point Process (TPP) and deep learning methodologies with point process theory to predict both spatial and temporal aspects of observer’s visual scanpaths. The proposed model is evaluated on five publicly available datasets, demonstrating superior performance compared to state-of-the-art approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new way to understand how our eyes move when we look at things. It’s like following a path that our eyes take as they jump from one thing to another. Right now, computers are good at guessing where our eyes will go next, but not so much about when and for how long. The authors came up with a new idea called TPP-Gaze, which helps computers understand both where and when we look at things. They tested it on five big datasets and found that their method works better than other ways to do this. |
Keywords
» Artificial intelligence » Attention » Deep learning
