In the Eye of the Beholder: A Survey of Models for Eyes and Gaze

By Dan Witzner Hansen, Qiang Ji. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010

1,563 citations recorded by the source corpus.

Subfields: Ophthalmology, Radiology, Nuclear Medicine and Imaging, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/79ced39c474df5d944323a394dc0d5923c14b410

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ophthalmology

In Radiology, Nuclear Medicine and Imaging

In Human-Computer Interaction

Citations in the corpus

Gaze locking: passive eye contact detection for human-object interaction (2013, background): “Hansen and Ji [17] and Morimoto and Mimica [26] provide excellent surveys of earlier work.”
Eye Tracking and Eye-Based Human–Computer Interaction (2014, methodology): “…processes have been used to model ﬁxation sequences of observers looking at objects with the goal of quantifying the similarity of eye movements (Hacisalihzade et al. 1992), to identify salient image features that affected the perception of visual realism (ElHelw et al. 2008), or to interpret…”
State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications (2018, background): “Hansen and Ji [HJ10] provide an extensive survey of the ﬁrst eye models and algorithms used for tracking gaze in images.”
Accurate Eye Centre Localisation by Means of Gradients (2011, background): “A survey on video-based eye detection and tracking can be found, for example, in (Hansen and Ji, 2010).”
Facial Landmark Detection: A Literature Survey (2018, background): “The facial landmark points around eyes can provide the initial guess of the pupil center positions for eye detection and eye gaze tracking (Hansen and Ji 2010).”
OpenFace 2.0: Facial Behavior Analysis Toolkit (2018, neutral): “these respective fields [18], [31], [58], [17].”
MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation (2017, background): “Gaze estimation methods can generally be distinguished as modelbased or appearance-based [22].”
The influence of calibration method and eye physiology on eyetracking data quality (2012, result): “Zhang and Hornof (2011), Hansen and Ji (2009), and others have reported similar results. Furthermore, accuracy depends strongly on the particular characteristics of the individual participant (Hornof & Halverson, 2002), with head movements, astigmatism, and eyelid closure being particularly troubles”
Manifold Alignment for Person Independent Appearance-Based Gaze Estimation (2014, background): “RELATED WORK Gaze estimation approaches are commonly divided into feature-based and appearance-based methods (see [2]).”
Efficient eye typing with 9-direction gaze estimation (2017, methodology): “The calibration process usually contains camera-calibration, geometric-calibration, personal calibration and gaze mapping calibration [4].”
It’s Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation (2016, background): “A large number of works in computer vision have studied the problem of estimating human eye gaze [7] given its importance for different applications, such as human-robot interaction [21], affective computing [4], and social signal processing [30].”
In the Eye of Beholder: Joint Learning of Gaze and Actions in First Person Video (2018, background): “In addition, there are small but non-negligible measurement errors in the eye-tracker itself [10].”