Convolutional Neural Network-Based Methods for Eye Gaze Estimation: A Survey

Abstract

Eye tracking is becoming a very important tool across many domains, including humancomputer-interaction, psychology, computer vision, and medical diagnosis. Different methods have been used to tackle eye tracking, however, some of them are inaccurate under real-world conditions, while some require explicit user calibration which can be burdensome. Some of these methods suffer from poor image quality and variable light conditions. The recent success and prevalence of deep learning have greatly improved the performance of eye-tracking. The availability of large-scale datasets has further improved the performance of deep learning-based methods. This paper presents a survey of the current state-of-the-art on deep learning-based gaze estimation techniques, with a focus on Convolutional Neural Networks (CNN). This paper also provides a survey on other machine learning-based gaze estimation techniques. This study aims to empower the research community with valuable and useful insights that can enhance the design and development of improved and efficient deep learning-based eye-tracking models. This study also provides information on various pre-trained models, network architectures, and open-source datasets that are useful for training deep learning models.

Remote Data Collection During a Pandemic: A New Approach for Assessing and Coding Multisensory Attention Skills in Infants and Young Children

“…While there have been previous successful examples of using a combination of eye tracking and ML to estimate gaze localizations (e.g., George and Routray, 2016;Akinyelu and Blignaut, 2020; and for a review, see Klaib et al, 2021), our approach was developed specifically for our three-screen video based protocol to be used with infants and children with data collected remotely and thus complements these previous approaches. Our goal was to develop a ML model that could be easily used and understood by individuals with little or no prior ML modeling experience.…”

User attention and behaviour in virtual reality art encounter

“…Multiple deep learning models were used for skeleton-based human activity and hand gesture recognition [31]. A survey paper [1] reviewed several CNN-based methods for predicting viewers' eye gaze based on images sampled from front-facing Therefore are well-suited for our complex tasks of analysing user attention from both movements and eye gaze. A range of deep learning classification models are built as means to explore how user behaviours are attributed to their personal background.…”

Convolutional Neural Network-Based Technique for Gaze Estimation on Mobile Devices

“…This coordinate system permits a model to estimate gaze coordinates that can be generalized to multiple devices (such as laptops and smartphones) and orientations (portrait or landscape), depending on where the camera is positioned on the screen. It takes advantage of the fact that the front-facing camera is typically on the same plane to the screen, and it is angled perpendicular to the screen (Krafka et al, 2016;Akinyelu and Blignaut, 2020).…”