TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking
arXiv:1504.06755
Abstract
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.
9 pages, 14 figures
Cited by in corpus (9)
- Learning Visual Importance for Graphic Designs and Data Visualizations
- SaltiNet: Scan-path Prediction on 360 Degree Images using Saliency Volumes
- Seeing with Humans: Gaze-Assisted Neural Image Captioning
- Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output
- Learning Uncertain Convolutional Features for Accurate Saliency Detection
- Entity Recognition at First Sight: Improving NER with Eye Movement Information
- MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation
- Saliency Revisited: Analysis of Mouse Movements versus Fixations
- FastSal: a Computationally Efficient Network for Visual Saliency Prediction