https://github.com/aeye-lab/eyettention

https://github.com/aeye-lab/eyettention

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: arxiv.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (12.2%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: aeye-lab
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 3.8 MB
Statistics
  • Stars: 11
  • Watchers: 4
  • Forks: 3
  • Open Issues: 0
  • Releases: 2
Created over 3 years ago · Last pushed over 2 years ago
Metadata Files
Readme License

README.md

Eyettention: An Attention-based Dual-Sequence Model for Predicting Human Scanpaths during Reading

paper

In this paper, we develop Eyettention, the first dual-sequence model that simultaneously processes the sequence of words and the chronological sequence of fixations. The alignment of the two sequences is achieved by a cross-sequence attention mechanism. We show that Eyettention outperforms state-of-the-art models in predicting scanpaths. We provide an extensive within- and across-data set evaluation on different languages. An ablation study and qualitative analysis support an in-depth understanding of the model's behavior.

Setup

Clone repository:

git clone git@github.com:aeye-lab/Eyettention

or

git clone https://github.com/aeye-lab/Eyettention and change to the cloned repo via cd Eyettention.

Install dependencies:

pip install -r requirements.txt

Dataset

For CELER dataset, you need to follow the instructions https://github.com/berzak/celer In order to run the experiments, place the downloaded CELER dataset in the /Data/ folder.

Run Experiments

For Chinese BSC dataset:

python main_BSC.py --test_mode='text' python main_BSC.py --test_mode='subject' python main_BSC_NRS_setting.py python main_BSC_reader_identifier.py

For English CELER dataset:

python main_celer.py --test_mode='text' python main_celer.py --test_mode='subject' python main_celer_NRS_setting.py python main_celer_reader_identifier.py

Cite our work

If you use our code for your research, please consider citing our paper:

bibtex @article{deng2023eyettention, title={Eyettention: {A}n Attention-based Dual-Sequence Model for Predicting Human Scanpaths during Reading}, author={Deng, Shuwen and Reich, David R and Prasse, Paul and Haller, Patrick and Scheffer, Tobias and J{\"a}ger, Lena A}, journal={Proceedings of the {ACM} on Human-Computer Interaction}, volume={7}, number={ETRA}, pages={1--24}, year={2023}, publisher={ACM New York, NY, USA} }

Owner

  • Name: AEye
  • Login: aeye-lab
  • Kind: organization
  • Email: lejaeger@uni-potsdam.de

AEye is a junior research group within the University of Potsdam. Members of AEye work on the intersection of machine learning and eye tracking.

GitHub Events

Total
  • Issues event: 2
  • Watch event: 4
  • Issue comment event: 1
Last Year
  • Issues event: 2
  • Watch event: 4
  • Issue comment event: 1

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 1
  • Total pull requests: 0
  • Average time to close issues: about 4 hours
  • Average time to close pull requests: N/A
  • Total issue authors: 1
  • Total pull request authors: 0
  • Average comments per issue: 1.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: about 4 hours
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 1.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • BaiYunpeng1949 (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels