English

Decoding Attention from Gaze: A Benchmark Dataset and End-to-End Models

Computer Vision and Pattern Recognition 2022-11-22 v1 Machine Learning

Abstract

Eye-tracking has potential to provide rich behavioral data about human cognition in ecologically valid environments. However, analyzing this rich data is often challenging. Most automated analyses are specific to simplistic artificial visual stimuli with well-separated, static regions of interest, while most analyses in the context of complex visual stimuli, such as most natural scenes, rely on laborious and time-consuming manual annotation. This paper studies using computer vision tools for "attention decoding", the task of assessing the locus of a participant's overt visual attention over time. We provide a publicly available Multiple Object Eye-Tracking (MOET) dataset, consisting of gaze data from participants tracking specific objects, annotated with labels and bounding boxes, in crowded real-world videos, for training and evaluating attention decoding algorithms. We also propose two end-to-end deep learning models for attention decoding and compare these to state-of-the-art heuristic methods.

Keywords

Cite

@article{arxiv.2211.10966,
  title  = {Decoding Attention from Gaze: A Benchmark Dataset and End-to-End Models},
  author = {Karan Uppal and Jaeah Kim and Shashank Singh},
  journal= {arXiv preprint arXiv:2211.10966},
  year   = {2022}
}

Comments

To be published in Proceedings of the NeurIPS 2022 Gaze Meets ML Workshop

R2 v1 2026-06-28T06:18:30.351Z