Gaze locking: passive eye contact detection for human-object interaction

By Brian A. Smith, Qi Yin, Steven K. Feiner, Shree K. Nayar. ACM Symposium on User Interface Software and Technology, 2013

373 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/06f02199690961ba52997cde1527e714d2b3bf8f

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

DEEP eye contact detector: Robust eye contact bid detection using convolutional neural network (2017, neutral): “Smith et al. [21] proposed an algorithm to detect gaze-locking (looking at a camera) faces using eye appearances and PCA+MDA.”
Photo-Realistic Monocular Gaze Redirection Using Generative Adversarial Networks (2019, methodology): “iment indicating that our technique can ﬁll in unseen gaze angles. First, we constructed two datasets. The raw dataset contains all the eye images with 10 pitch angles from the Columbia Gaze Dataset [27]. The augmented dataset contains the images from the raw dataset. Furthermore, we took the images”
Learning an appearance-based gaze estimator from one million synthesised images (2016, background): “While some previous datasets captured participants from a sparse and discrete set of different camera angles [Smith et al. 2013; Sugano et al. 2014], we instead specified the transforms of camera and eyeball continuously, allowing us to synthesize dense training data.”
It’s Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation (2016, background): “Consequently, recent years have seen an increasing number of gaze estimation datasets collected in everyday settings [9, 19, 24], including some at large scale [13, 36], or consisting of synthetic data [25, 32, 33].”
Gaze360: Physically Unconstrained Gaze Estimation in the Wild (2019, methodology): “The comparison datasets we use are: Columbia [20] - high-resolution close-up faces; MPIIFaceGaze [31] - faces captured by webcams; RTGENE [4] - low-resolution faces using in-painting to mask out eye-tracking glasses; Gaze360 (Ours) - faces with varying resolution; For those datasets where no officia”
Appearance-based gaze estimation in the wild (2015, background): “Because most existing gaze estimation datasets are de signed for coarse gaze estimation, the sampling density of gaze and head pose space is not sufficient to train appearance-based gaze estimators [29, 45, 46, 37] (see Ta ble 1 for an overview of existing datasets).”
MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation (2017, methodology): “For example, Schneider et al. performed a cross-person evaluation on theColumbia dataset [13] with 21 gaze points for one frontal head pose of 56 participants [5].”
RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments (2018, background): “In the Columbia Gaze dataset [52], subjects have their head placed on a chin rest and are asked to fixate on a dot displayed on a wall whilst their eye gaze is recorded.”
Learning-by-Synthesis for Appearance-Based 3D Gaze Estimation (2014, methodology): “However, their sampling density of gaze directions is rather limited (at most 21 directions per head pose [29]) because their purpose is for learning coarse gaze classifiers.”
Controllable Continuous Gaze Redirection (2020, methodology): “We randomly select 85 subjects from the Columbia Gaze [29] and ours for training, and use the others for testing.”
Manifold Alignment for Person Independent Appearance-Based Gaze Estimation (2014, methodology): “[28] used a commercial system by Omron [30].”