Learning relevant eye movement feature spaces across users


Hussain, Zakria, Pasupa, Kitsuchart and Shawe-Taylor, John (2010) Learning relevant eye movement feature spaces across users. At Proceedings of the 6th Biennial Symposium on Eye Tracking Research & Applications (ETRA'2010), Austin, TX, USA, 22 - 24 Mar 2010. ACM, 181-185. (Submitted).

Download

[img] PDF - Accepted Version
Download (732Kb)

Description/Abstract

In this paper we predict the relevance of images based on a lowdimensional feature space found using several users’ eye movements. Each user is given an image-based search task, during which their eye movements are extracted using a Tobii eye tracker. The users also provide us with explicit feedback regarding the relevance of images. We demonstrate that by using a greedy Nystrom algorithm on the eye movement features of different users, we can find a suitable low-dimensional feature space for learning. We validate the suitability of this feature space by projecting the eye movement features of a new user into this space, training an online learning algorithm using these features, and showing that the number of mistakes (regret over time) made in predicting relevant images is lower than when using the original eye movement features. We also plot Recall-Precision and ROC curves, and use a sign test to verify the statistical significance of our results.

Item Type: Conference or Workshop Item (Poster)
Additional Information: Event Dates: 22-24 March 2010
Related URLs:
Keywords: Feature selection, Eye movement features, Online learning, Nystrom method, Tobii eye-tracker
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science
ePrint ID: 268502
Date Deposited: 12 Feb 2010 00:16
Last Modified: 27 Mar 2014 20:15
Publisher: ACM
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/268502

Actions (login required)

View Item View Item