A Learning Paradigm for Selecting Few Discriminative Stimuli in Eye-Tracking Research
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025
DOI: 10.1109/tpami.2025.3573729 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025. Verfasst von Wenqi Zhong und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Eye-Tracking Technology, Eye Movements, Machine Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 74 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key-Area Research and Development Program of Shaanxi Province.
Abstract (Originalsprache)
Eye-tracking is a reliable method for quantifying visual information processing and holds significant potential for group recognition, such as identifying autism spectrum disorder (ASD). However, eye-tracking research typically faces the heterogeneity of stimuli and is time-consuming due to the large number of observed stimuli. To address these issues, we first mathematically define the stimulus selection problem and introduce the concept of stimulus discrimination ability to reduce the computational complexity of the solution. Then, we construct a scanpath-based recognition model to mine the stimulus discrimination ability. Specifically, we propose cross-subject entropy and cross-subject divergence scores for quantitatively evaluating stimulus discrimination ability, effectively capturing differences in intra-group collective trends and inter-subject consistency within a group. Furthermore, we propose an iterative learning mechanism that employs stimulus-wise attention to focus on discriminative stimuli for discrimination purification. In the experiment, we construct an ASD eye-tracking dataset with diverse stimulus types and conduct extensive tests on three representative models to validate our approach. Remarkably, our method demonstrates superior performance using only 10 selected stimuli compared to models utilizing 220 stimuli. Additionally, we perform experiments on another eye-tracking task, gender prediction, to further validate our method. We believe that our approach is both simple and flexible for integration into existing models, promoting large-scale ASD screening and extending to other eye-tracking research domains.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Natural Science Foundation of China
- Key-Area Research and Development Program of Shaanxi Province
Zitieren
APA
Zhong, W., Xia, C., Yu, L., Li, K., Li, Z., Zhang, D., & Han, J. (2025). A Learning Paradigm for Selecting Few Discriminative Stimuli in Eye-Tracking Research. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2025.3573729
Vancouver
Zhong W, Xia C, Yu L, Li K, Li Z, Zhang D, et al. A Learning Paradigm for Selecting Few Discriminative Stimuli in Eye-Tracking Research. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025. doi:10.1109/tpami.2025.3573729
BibTeX
@article{Zhong2025,
author = {Zhong, Wenqi and Xia, Chen and Yu, Linzhi and Li, Kuan and Li, Zhongyu and Zhang, Dingwen and Han, Junwei},
title = {A Learning Paradigm for Selecting Few Discriminative Stimuli in Eye-Tracking Research},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
doi = {10.1109/tpami.2025.3573729}
}
EUVIMED