I Can See What You Think The Mental Image Revealed by Gaze Tracking

CHI 2019
James Hays (Georgia Institute of Technology)      Kenneth Holmqvist (Universitaet Regensburg)      Marc Alexa (Computer Graphics, TU Berlin)

When people mentally imagine a photograph, their eyes move as if they were actually looking at that photo. We record eye movements while a photo is recalled from memory and introduce algorithms that can determine which photo is being imagined.




Abstract

Humans involuntarily move their eyes when retrieving an image from memory. This motion is often similar to actually observing the image. We suggest to exploit this behavior as a new modality in human computer interaction, using the motion of the eyes as a descriptor of the image. Interaction requires the user's eyes to be tracked but no voluntary physical activity. We perform a controlled experiment and develop matching techniques using machine learning to investigate if images can be discriminated based on the gaze patterns recorded while users merely think about image. Our results indicate that image retrieval is possible with an accuracy significantly above chance. We also show that this result generalizes to images not used during training of the classifier and extends to uncontrolled settings in a realistic scenario.


Download File "The Mental Image Revealed by Gaze Tracking"
[pdf, 5.5 MB]



Video Preview




Dataset will be available before the conference dates.


Source code will be available before the conference dates.


Press articles



Acknowledgments

We would like to thank Minjung Kim for narrating the video and all participants for joining our experiment.