TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking

04/25/2015
by   Pingmei Xu, et al.
0

Traditional eye tracking requires specialized hardware, which means collecting gaze data from many observers is expensive, tedious and slow. Therefore, existing saliency prediction datasets are order-of-magnitudes smaller than typical datasets for other vision recognition tasks. The small size of these datasets limits the potential for training data intensive algorithms, and causes overfitting in benchmark evaluation. To address this deficiency, this paper introduces a webcam-based gaze tracking system that supports large-scale, crowdsourced eye tracking deployed on Amazon Mechanical Turk (AMTurk). By a combination of careful algorithm and gaming protocol design, our system obtains eye tracking data for saliency prediction comparable to data gathered in a traditional lab setting, with relatively lower cost and less effort on the part of the researchers. Using this tool, we build a saliency dataset for a large number of natural images. We will open-source our tool and provide a web server where researchers can upload their images to get eye tracking results from AMTurk.

READ FULL TEXT

page 1

page 4

page 5

page 6

page 7

page 8

research
06/30/2019

Predicting video saliency using crowdsourced mouse-tracking data

This paper presents a new way of getting high-quality saliency maps for ...
research
05/30/2017

Saliency Revisited: Analysis of Mouse Movements versus Fixations

This paper revisits visual saliency prediction by evaluating the recent ...
research
08/25/2023

Open Gaze: Open Source eye tracker for smartphone devices using Deep Learning

Eye tracking has been a pivotal tool in diverse fields such as vision re...
research
02/28/2019

EyeDoc: Documentation Navigation with Eye Tracking

We demonstrate EyeDoc, a tool for navigating software documentation with...
research
03/30/2023

Gazealytics: A Unified and Flexible Visual Toolkit for Exploratory and Comparative Gaze Analysis

We present a novel, web-based visual eye-tracking analytics tool called ...
research
05/16/2019

Leverage eye-movement data for saliency modeling: Invariance Analysis and a Robust New Model

Data size is the bottleneck for developing deep saliency models, because...
research
08/26/2023

Modeling Programmer Attention as Scanpath Prediction

This paper launches a new effort at modeling programmer attention by pre...

Please sign up or login with your details

Forgot password? Click here to reset