Image classification models are becoming a popular method of analysis for scanpath classification. To implement these models, gaze data must first be reconfigured into a 2D image. However, this step gets relatively little attention in the literature as focus is mostly placed on model configuration. As standard model architectures have become more accessible to the wider eye-tracking community, we highlight the importance of carefully choosing feature representations within scanpath images as they may heavily affect classification accuracy. To illustrate this point, we create thirteen sets of scanpath designs incorporating different eye-tracking feature representations from data recorded during a task-based viewing experiment. We evaluate each scanpath design by passing the sets of images through a standard pre-trained deep learning model as well as a SVM image classifier. Results from our primary experiment show an average accuracy improvement of 25 percentage points between the best-performing set and one baseline set.

Byrne, S., Maquiling, V., Reynolds, A., Polonio, L., Castner, N., Kasneci, E. (2023). Exploring the Effects of Scanpath Feature Engineering for Supervised Image Classification Models. In Proceedings of the ACM on Human-Computer Interaction (pp.1-18). New York NY: Association for Computing Machinery Inc. [10.1145/3591130].

Exploring the Effects of Scanpath Feature Engineering for Supervised Image Classification Models

Polonio, Luca;
2023

Abstract

Image classification models are becoming a popular method of analysis for scanpath classification. To implement these models, gaze data must first be reconfigured into a 2D image. However, this step gets relatively little attention in the literature as focus is mostly placed on model configuration. As standard model architectures have become more accessible to the wider eye-tracking community, we highlight the importance of carefully choosing feature representations within scanpath images as they may heavily affect classification accuracy. To illustrate this point, we create thirteen sets of scanpath designs incorporating different eye-tracking feature representations from data recorded during a task-based viewing experiment. We evaluate each scanpath design by passing the sets of images through a standard pre-trained deep learning model as well as a SVM image classifier. Results from our primary experiment show an average accuracy improvement of 25 percentage points between the best-performing set and one baseline set.
paper
Human-Computer Interaction; Eye Tracking, Machine Learning, Economics, Decision Making, Neural Networks
English
ACM Symposium of Eye Tracking Research & Applications (ETRA) - May 30 to June 2, 2023
2023
Sean Anthony Byrne, Virmarie Maquiling, Adam Peter Frederick Reynolds, Luca Polonio, Nora Castner, Enkelejda Kasneci
Nichols, J
Proceedings of the ACM on Human-Computer Interaction
2023
7
ETRA
1
18
161
https://dl.acm.org/doi/10.1145/3591130
reserved
Byrne, S., Maquiling, V., Reynolds, A., Polonio, L., Castner, N., Kasneci, E. (2023). Exploring the Effects of Scanpath Feature Engineering for Supervised Image Classification Models. In Proceedings of the ACM on Human-Computer Interaction (pp.1-18). New York NY: Association for Computing Machinery Inc. [10.1145/3591130].
File in questo prodotto:
File Dimensione Formato  
Byrne-2023-Proceed ACM Human-Computer Interact-VoR.pdf

Solo gestori archivio

Descrizione: Intervento a convegno
Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Tutti i diritti riservati
Dimensione 6.72 MB
Formato Adobe PDF
6.72 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/416496
Citazioni
  • Scopus 4
  • ???jsp.display-item.citation.isi??? ND
Social impact