GAZEL: Runtime Gaze Tracking for Smartphones

Park, Joonbeom; Park, Seonghoon; Cha, Hojung

doi:10.1109/percom50583.2021.9439113

Cited by 9 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…J. Park et al (2021) argue that many Gaze-Capture images represent nontypical use cases (e.g., arms being raised above the head). They therefore train GAZEL with data collected from ten tablet users under professedly more typical usage scenarios.…”

Section: Initialization and Calibration Of The Gaze Estimation Models...mentioning

confidence: 99%

“…• Interaction correlation: The model is continuously re-calibrated using click data as calibration points (Allen & Jensen, 2014;Klein Salvalaio & Ramos, 2019;Papoutsaki et al, 2016;J. Park et al, 2021).…”

Section: Initialization and Calibration Of The Gaze Estimation Models...mentioning

confidence: 99%

“…With an error of 9.5% of the diagonal screen extension, GAZEL reports the best performance on phones (J. Park et al, 2021). On desktops, the error of TurkerGaze gets as low as 2.3% (Xu et al, 2015).…”

Section: Accuracymentioning

confidence: 99%

“…While the evaluations, excepting TurkerGaze and Optimeyes, did not exclude subjects with glasses, four authors report a negative effect (Huynh et al, 2022;J. Park et al, 2021;S.…”

Section: Accuracymentioning

confidence: 99%

See 3 more Smart Citations

Webcam Eye Tracking for Desktop and Mobile Devices: A Systematic Review

Heck,

Becker,

Deutscher

2023

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Building the Internet of Behaviors (IOB) obviously requires capturing human behavior. Sensor input from eye tracking has been widely used for profiling in market research, adaptive user interfaces, and other smart systems, but requires dedicated hardware. The wide spread of webcams in consumer devices like phones, notebooks, and smart TVs has fostered eye tracking with commodity cameras. In this paper, we present a systematic review across the IEEE and ACM databases -complemented by snowballing and input from eye tracking experts at CHI 2021 -to list and characterize publicly available software for webcam eye tracking that estimate the point-ofregard with no additional hardware. Information from articles was supplemented by searching author websites and code repositories, and contacting authors. 16 eye trackers were found that can be used. The restrictions regarding license terms and technical performance are presented, enabling developers to choose an appropriate software for their IoB application.

show abstract

Section: Initialization and Calibration Of The Gaze Estimation Models...mentioning

confidence: 99%

Section: Initialization and Calibration Of The Gaze Estimation Models...mentioning

confidence: 99%

Section: Accuracymentioning

confidence: 99%

“…While the evaluations, excepting TurkerGaze and Optimeyes, did not exclude subjects with glasses, four authors report a negative effect (Huynh et al, 2022;J. Park et al, 2021;S.…”

Section: Accuracymentioning

confidence: 99%

See 2 more Smart Citations

Webcam Eye Tracking for Desktop and Mobile Devices: A Systematic Review

Heck,

Becker,

Deutscher

2023

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

show abstract

“…Shaoming Yan, Yuanliang Ju, and Rong Quan contributed equally to this work. intelligent interaction methods have also been explored on smartphones, such as voice control [5][6][7], gesture input [8][9][10][11] and eye-gaze interaction [12][13][14][15][16]. Eye-gaze interaction on smartphones refers to utilizing eye-and gaze-related information, such as gaze positions, gaze gestures, dwell time, and eye blinks, to control smartphones.…”

Section: Introductionmentioning

confidence: 99%

E2GCO: Event-driven Eye-Gaze-Controlled Operation for Smartphone Interaction

Liang,

Yan,

et al. 2024

Preprint

View full text Add to dashboard Cite

Existing gaze-based smartphone interaction methods generally need the auxiliary of hand motions to realize control, and most of them can achieve only simple control operations, which are far from practical smartphone control. To this end, we propose a novel eye-gaze-based smartphone interaction method named Event-driven Eye-Gaze-Controlled Operation ($E^2GCO$), which can realize comprehensive smartphone control operations just using human eyes and gazes. We designed four pairs of eye-gaze-based interaction actions that are easy to implement and distinguish, based on which $E^2GCO$ can control all kinds of smartphone pages. Before the interaction, an anti-jitter strategy-based gaze estimation method is exploited to solve the jitter problem of human eye fixation and detect both accurate and stable human gaze locations on smartphone screens, even when the users are moving. The interaction can be executed more accurately based on the stable and accurate gaze locations. In addition, the event camera technology is introduced in $E^2GCO$ to significantly decrease its power consumption, making $E^2GCO$ more power-efficient to deploy on smartphones. We have implemented the prototype of $E^2GCO$ on different brands of smartphones and conducted a comprehensive user study to validate its efficacy. The user study demonstrates $E^2GCO$'s superior smartphone control capabilities across various scenarios.

show abstract