PET: An Eye-tracking Dataset for Animal-centric PASCAL Object Classes
Abstract
We present the Pascal animal classes Eye Tracking database. Our database comprises eye movement recordings compiled from forty users for the bird, cat, cow, dog, horse and sheep {trainval} sets from the VOC 2012 image set. Different from recent eye-tracking databases such as \cite{kiwon_cvpr13_gaze,PapadopoulosCKF14}, a salient aspect of PET is that it contains eye movements recorded for both the free-viewing and visual search task conditions. While some differences in terms of overall gaze behavior and scanning patterns are observed between the two conditions, a very similar number of fixations are observed on target objects for both conditions. As a utility application, we show how feature pooling around fixated locations enables enhanced (animal) object classification accuracy.
Keywords
Cite
@article{arxiv.1604.01574,
title = {PET: An Eye-tracking Dataset for Animal-centric PASCAL Object Classes},
author = {Syed Omer Gilani and Ramanathan Subramanian and Yan Yan and David Melcher and Nicu Sebe and Stefan Winkler},
journal= {arXiv preprint arXiv:1604.01574},
year = {2016}
}
Comments
Int'l Conference on Multimedia and Expo 2015