BubbleView: An alternative to eye-tracking for crowdsourcing image importance

Human eye fixations can be used as a heatmap of saliency for an image
Just as the pattern of human eye fixations can be used as a heatmap of saliency for an image (a), the pattern of BubbleView clicks can be used as a heatmap of importance for an image (b). An eye tracking set-up (pictured: EyeLink1000) is a way to collect human eye fixations in the lab setting (c), whereas the BubbleView interface can be launched online and feasibly scale up the collection of crowdsourced data (d).
Abstract
In this paper, we present BubbleView, an alternative methodology for eye tracking using discrete mouse clicks to measure which information people consciously choose to examine. BubbleView is a mouse-contingent, moving-window interface in which participants are presented with a series of blurred images and click to reveal "bubbles" - small, circular areas of the image at original resolution, similar to having a confined area of focus like the eye fovea. Across 10 experiments with 28 different parameter combinations, we evaluated BubbleView on a variety of image types: information visualizations, natural images, static webpages, and graphic designs, and compared the clicks to eye fixations collected with eye-trackers in controlled lab settings. We found that BubbleView clicks can both (i) successfully approximate eye fixations on different images, and (ii) be used to rank image and design elements by importance. BubbleView is designed to collect clicks on static images, and works best for defined tasks such as describing the content of an information visualization or measuring image importance. BubbleView data is cleaner and more consistent than related methodologies that use continuous mouse movements. Our analyses validate the use of mouse-contingent, moving-window methodologies as approximating eye fixations for different image and task types.
Materials
PDF | DOI | Homepage | Supplement | BibTeX
Authors
Nam Wook Kim
Zoya Bylinskii
Krzysztof Z. Gajos
Aude Oliva
Fredo Durand
Hanspeter Pfister
Citation
Thumbnail image for publication titled: BubbleView: An alternative to eye-tracking for crowdsourcing image importance
BubbleView: An alternative to eye-tracking for crowdsourcing image importance

Nam Wook Kim, Zoya Bylinskii, Michelle A. Borkin, Krzysztof Z. Gajos, Aude Oliva, Fredo Durand, and Hanspeter Pfister. ACM Transactions on Computer-Human Interaction—TOCHI. 2017. DOI: 10.1145/3131275

PDF | DOI | Homepage | Supplement | BibTeX


Khoury Vis Lab — Northeastern University
West Village H, Room 302
440 Huntington Ave, Boston, MA 02115, USA