Sorry, you need to enable JavaScript to visit this website.

AN EYE-TRACKING DATABASE OF VIDEO ADVERTISING

Citation Author(s):
Hantao Liu
Submitted by:
Lucie LEVEQUE
Last updated:
10 September 2019 - 10:48pm
Document Type:
Poster
Document Year:
2019
Event:
Presenters:
Lucie Lévêque
Paper Code:
1540
Categories:
 

Reliably predicting where people look in images and videos remains challenging and requires substantial eye-tracking data to be collected and analysed for various applications. In this paper, we present an eye-tracking study where twenty-eight participants viewed forty still scenes of video advertising. First, we analyse human attentional behaviour based on gaze data. Then, we evaluate to what extent a machine – saliency model – can predict human behaviour. Experimental results show that there is a significant gap between human and machine in visual saliency. The resulting eye-tracking data would benefit the development of saliency models for video advertising or other relevant applications. The eye-tracking data are made publicly available to the research community.

up
0 users have voted: