| | |
Summary: Decoding what people see from where they look:
predicting visual stimuli from scanpaths
Moran Cerf 1
, Jonathan Harel 1
, Alex Huth1
, Wolfgang Einh¨auser2
, and
Christof Koch1
1
California Institute of Technology, Pasadena, CA, USA
2
Philipps-University Marburg, Germany
Abstract. Saliency algorithms are applied to correlate with the overt
attentional shifts, corresponding to eye movements, made by observers
viewing an image. In this study, we investigated if saliency maps could
be used to predict which image observers were viewing given only scan-
path data. The results were strong: in an experiment with 441 trials,
each consisting of 2 images with scanpath data - pooled over 9 subjects -
belonging to one unknown image in the set, in 304 trials (69%) the cor-
rect image was selected, a fraction significantly above chance, but much
|
