Scalable Webcam Eye Tracking by Learning from User Interactions

Papoutsaki, Alexandra

doi:10.1145/2702613.2702627

Cited by 175 publications

(206 citation statements)

References 3 publications

Supporting

Mentioning

202

Contrasting

Unclassified

Order By: Relevance

“…The methodology and models can easily be adapted to other visual domains, such as websites [22]. As better webcam-based eyetracking methods become available (e.g., [24,37,48]) possibilities also open up for directly training our model from eye movement data. Future work can also explore the use of importance predictions to offer more targeted design feedback and to provide automated suggestions to a user.…”

Section: Discussionmentioning

confidence: 99%

Learning Visual Importance for Graphic Designs and Data Visualizations

Bylinskii

Kim

O’Donovan

et al. 2017

Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology

145

View full text Add to dashboard Cite

Knowing where people look and click on visual designs can provide clues about how the designs are perceived, and where the most important or relevant content lies. The most important content of a visual design can be used for effective summarization or to facilitate retrieval from a database. We present automated models that predict the relative importance of different elements in data visualizations and graphic designs. Our models are neural networks trained on human clicks and importance annotations on hundreds of designs. We collected a new dataset of crowdsourced importance, and analyzed the predictions of our models with respect to ground truth importance and human eye movements. We demonstrate how such predictions of importance can be used for automatic design retargeting and thumbnailing. User studies with hundreds of MTurk participants validate that, with limited post-processing, our importance-driven applications are on par with, or outperform, current state-of-the-art methods, including natural image saliency. We also provide a demonstration of how our importance predictions can be built into interactive design tools to offer immediate feedback during the design process

show abstract

Section: Discussionmentioning

confidence: 99%

Learning Visual Importance for Graphic Designs and Data Visualizations

Bylinskii

Kim

O’Donovan

et al. 2017

Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology

145

View full text Add to dashboard Cite

show abstract

“…Another tool that widens online research capabilities is remote, webcam-based eye tracking. An implementation of the WebGazer.js library (Papoutsaki et al, 2016) for eye-tracking is also being integrated into the platform. This permits rough eye-tracking, and head position tracking, using the user's webcam.…”

Section: Future Featuresmentioning

confidence: 99%

Gorilla in our Midst: An online behavioral experiment builder

Anwyl-Irvine

Massonnié

Flitton

et al. 2018

Preprint

169

162

View full text Add to dashboard Cite

Behavioural researchers are increasingly conducting their studies online to gain access to large and diverse samples that would be difficult to get in a laboratory environment. However, there are technical access barriers to building experiments online, and web-browsers can present problems for consistent timingan important issue with reaction time-sensitive measures. For example, to ensure accuracy and test-retest reliability in presentation and response recording, experimenters need a working knowledge of programming languages such as JavaScript. We review some of the previous and current tools for online behavioural research, and how well they address the issues of usability and timing. We then present The Gorilla Experiment Builder (gorilla.sc) a fully tooled experiment authoring and deployment platform, designed to resolve many timing issues, and make reliable online experimentation open and accessible to a wider range of technical abilities. In order to demonstrate the platform's aptitude for accessible, reliable and scalable research, we administered the task with a range of participant groups (primary school children and adults), settings (without supervision, at home, and under supervision, in schools and public engagement events), equipment (own computers, computer supplied by researcher), and connection types (personal internet connection, mobile phone 3G/4G). We used a simplified flanker task, taken from the Attentional Networks Task (Rueda, Posner, & Rothbart, 2004). We replicated the 'conflict network' effect in all these populations, demonstrating the platform's capability to run reaction timesensitive experiments. Unresolved limitations of running experiments online are then discussed, along with potential solutions, and some future features of the platform.

show abstract

“…It is easy to use as well as it has been proven to be quite reliable and accurate. The algorithm used for our prototype uses similar underlying factors as the prototype discussed in [47]. The algorithm uses a new method of storing and analyzing the eye tracking data.…”

Section: The Algorithm and Prototypementioning

confidence: 99%