Paper Info
Title
Looking Into Saliency Model via Space-Time Visualization.
Abstract
We introduce a visual analytics method to analyze eye-tracking data and saliency models for dynamic stimuli, such as video or animated graphics. The focus lies on the analysis of the different performance of saliency models in contrast to human observers to identify trends in the general viewing behavior, including time sequences of attentional synchrony and objects with a strong attentional focus. By using a space-time cube visualization in combination with clustering, the dynamic stimuli and associated eye gazes as well as the attention maps from saliency models can be analyzed in a static three-dimensional representation. We propose algorithms to keep the appearance of the computer's attention data in line with the human's eye-tracking data. The analytical process is supported by multiple coordinated views that allow the user to focus on different aspects of spatial and temporal information in eye gaze data and saliency map. By comparing attention data from both human and computer incorporated with the spatiotemporal characteristics, we are able to find the different patterns within human and computer algorithms. We list our key findings to help developing better saliency detection algorithms.
Year
DOI
Venue
2016
10.1109/TMM.2016.2613681
IEEE Trans. Multimedia
Keywords
Field
DocType
Data visualization,Visualization,Computational modeling,Analytical models,Feature extraction,Data models,Computers
Graphics,Computer vision,Data modeling,Data visualization,Pattern recognition,Computer science,Salience (neuroscience),Visualization,Visual analytics,Eye tracking,Artificial intelligence,Cluster analysis
Journal
Volume
Issue
ISSN
18
11
1520-9210
Citations 
PageRank 
References 
0
0.34
29
Authors
3
Name
Order
Citations
PageRank
Haoran Liang100.34
Ronghua Liang237642.60
Guo-Dao Sun317111.24