Toward Everyday Gaze Input

Feit, Anna Maria; Williams, Shane; Toledo, Arturo; Paradiso, Ann; Kulkarni, Harish; Kane, Shaun K.; Morris, Meredith Ringel

doi:10.1145/3025453.3025599

Cited by 160 publications

(60 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The eye tracker was carefully calibrated before each session to ensure the binocular tracking performance. The accuracy of this eye tracker is around 0.6° and 0.9° in the x-and ydirection, respectively, and its precisions in both direction are around 0.9° (Feit et al, 2017). A post-experiment interview confirmed that participants were able to fully focus on the visual target in the non-math sections, and 8 that the mental arithmetic required much cognitive effort.…”

Section: Methodsmentioning

confidence: 73%

“…This attempt alleviates the constraint of the expensive research-grade eye tracker as pointed out by Bixler and D'Mello (2016). Although EyeX gives a similar accuracy (offset from the true gaze point) as Tobii Pro X2-60 as well as a reasonable precision (Feit et al, 2017) and its firmware is optimized for real-time interaction (Tobii AB, 2018), its frame rate still limits the accurate detection of some saccadic behaviours. This might affect our comparison of using the "classic" eye movement features, but it is currently unavoidable as research-grade eye trackers are too expensive for home-use intelligent interfaces.…”

Section: Discussionmentioning

confidence: 99%

“…We recorded the screen video as well as the facial video using a webcam mounted on the monitor. Due to the decrease of eye tracking accuracy near the screen edges (Feit et al, 2017), we placed the video stimulus in the centre of the screen with a size of 18.1 cm by 10.2 cm, which is the default size of YouTube video in our setting. Participants were allowed to sit freely but recommended to avoid significant head movements.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Moment-to-Moment Detection of Internal Thought during Video Viewing from Eye Vergence Behavior

Huang

Ngai

et al. 2019

Proceedings of the 27th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Internal thought refers to the process of directing attention away from a primary visual task to internal cognitive processing. Internal thought is a pervasive mental activity and closely related to primary task performance. As such, automatic detection of internal thought has significant potential for user modelling in intelligent interfaces, particularly for e-learning applications. Despite the close link between the eyes and the human mind, only few studies have investigated vergence behaviour during internal thought and none has studied moment-to-moment detection of internal thought from gaze. While prior studies relied on long-term data analysis and required a large number of gaze characteristics, we describe a novel method that is computationally light-weight and that only requires eye vergence information that is readily available from binocular eye trackers. We further propose a novel paradigm to obtain ground truth internal thought annotations that exploits human blur perception. We evaluate our method for three increasingly challenging detection tasks: (1) during a controlled math-solving task, (2) during natural viewing of lecture videos, and (3) during daily activities, such as coding, browsing, and reading. Results from these evaluations demonstrate the performance and robustness of vergence-based detection of internal thought and, as such, open up new directions for research on interfaces that adapt to shifts of mental attention. 2

show abstract

Section: Methodsmentioning

confidence: 73%

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Moment-to-Moment Detection of Internal Thought during Video Viewing from Eye Vergence Behavior

Huang

Ngai

et al. 2019

Proceedings of the 27th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…The third area of work is the study of the variability in the data obtained from medium-to low-cost eye trackers in field conditions. This is in anticipation of widespread use of gaze position as an additional input channel in the context of personal computing, e.g., (Feit et al, 2017).…”

Section: Previous Workmentioning

confidence: 99%

“…Reingold addresses the measurement of data quality with two methods based on an artificial eye so that the same stimulus is presented to different eye trackers for the purposes of performance comparison. Feit et al (2017) investigated the variability in data quality in a study of 80 people using two remote eye trackers in two conditions representing differences in ambient lighting conditions. One condition was intended to represent natural light and the other artificial light.…”

Section: Data Quality and Unrestrained Usementioning

confidence: 99%

Improving the performance of eye trackers with limited spatial accuracy and low sampling rates for reading analysis by heuristic fixation-to-word mapping

et al. 2018

View full text Add to dashboard Cite

The recent growth in low-cost eye-tracking systems makes it feasible to incorporate real-time measurement and analysis of eye position data into activities such as learning to read. It also enables field studies of reading behavior in the classroom and other learning environments. We present a study of the data quality provided by two remote eye trackers, one being a low-sampling-rate, low-cost system. Then we present two algorithms for mapping fixations derived from the data to the words being read. One is for immediate (or real-time) mapping of fixations to words and the other for deferred (or post hoc) mapping. Following this, an evaluation study is reported. Both studies were carried out in the classroom of a Finnish elementary school with students who were second graders. This study shows very high success rates in automatically mapping fixations to the lines of text being read when the mapping is deferred. The success rates for immediate mapping are comparable with those obtained in earlier studies, although here the data is collected some 10 min after initial calibration of low-sample (30 Hz) remote eye trackers, rather than a laboratory setting using high-sampling-rate trackers. The results provide a solid basis for developing systems for use in classrooms and other learning environments that can provide immediate automatic support with reading, and share data between a group of learners and the teacher of that group. This makes possible new approaches to the learning of reading and comprehension skills.

show abstract

Sensor technology in eating disorders research: A systematic review

Presseller

Patarinski

Fan

et al. 2022

Intl J Eating Disorders

View full text Add to dashboard Cite

Objective Sensor technologies offer exciting potential to objectively measure psychopathological correlates of eating pathology and eating disorder (ED) research utilizing sensors has rapidly proliferated in the past several years. The aims of the present review are: (1) characterize the types of sensors that have been utilized in ED research, (2) identify the psychopathological factors relevant to EDs that have been assessed using sensors, (3) describe the data supporting the validity and reliability of these sensors, (4) discuss limitations associated with these sensors, and (5) identify gaps that persist within the ED literature with regard to use of sensor technologies. Method A systematic search was conducted of PubMed, PsycINFO, Web of Science, ProQuest, and “gray” literature sources. Eligible publications were empirical studies that utilized sensors to measure at least one psychological variable among clinical ED populations. Results Sensors have been utilized with ED samples to measure eating behaviors, physical activity, sleep, autonomic nervous system activity, eyeblink startle response, visual attention, and visual‐haptic object integration. The reliability and validity of these sensors varies widely and there are a number of significant gaps that remain in the literature with regard to the types of sensors utilized, context in which sensors have been used, and populations studied. Discussion The existing literature utilizing sensors within ED research largely support the feasibility and acceptability of these tools. Sensors should continue to be utilized within the field, with a specific focus on examining the reliability and validity of these tools within ED samples and increasing the diversity of samples studied. Public Significance Statement Sensor technologies, such as those included in modern smartwatches, offer new opportunities to measure factors that may maintain or contribute to symptoms of eating disorders. This article describes the types of sensors that have been used in eating disorders research, challenges that may arise in using these sensors, and discusses new applications of these sensors that may be pursued in future research.

show abstract

Toward Everyday Gaze Input

Cited by 160 publications

References 38 publications

Moment-to-Moment Detection of Internal Thought during Video Viewing from Eye Vergence Behavior

Moment-to-Moment Detection of Internal Thought during Video Viewing from Eye Vergence Behavior

Improving the performance of eye trackers with limited spatial accuracy and low sampling rates for reading analysis by heuristic fixation-to-word mapping

Sensor technology in eating disorders research: A systematic review

Contact Info

Product

Resources

About